Model performance on MindsHub

See how models served through MindsHub Inference perform: response times, availability and cost, with current prices, API aliases and fallback routes.

Measurements refresh every 2 to 6 hours · About the data

All makers
Makers
Reasoning effort

Intelligence

Compare MindsHub’s read, our intelligence estimate from 1 to 10, across effort levels. Each dot is an effort level; the ring marks your selection. Higher scores suggest greater overall capability.

View

How to read the intelligence chart

Thick line: Range from the lowest to the highest intelligence estimate.Dot: one effort level.Ring: the effort selected in the toolbar. Dot: one effort level.

MindsHub’s read is a subjective estimate from 1 to 10 based on public benchmarks and rankings, not a precise measurement. Performance depends on your workload; test models on your own tasks.

For detailed benchmarks, refer to third party services such as Artificial Analysis, Epoch AI or similar.

Showing 46 models

Highest score at your selected effort level first.

All settings, grouped by model. Highest-scored model first.

  • Claude Fable 5.2effort: low to maxClaude Fable 5.2 · effort: lowIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Fable 5.2 · effort: mediumIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Fable 5.2 · effort: highIntelligence estimate9.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Fable 5.2 · effort: xhighIntelligence estimate9.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Fable 5.2 · effort: maxIntelligence estimate10 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8.5–10, low 8.5, medium 9, high 9.5, xhigh 9.5, max 10
  • Claude Opus 5.5effort: low to maxClaude Opus 5.5 · effort: lowIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Opus 5.5 · effort: mediumIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Opus 5.5 · effort: highIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Opus 5.5 · effort: xhighIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Opus 5.5 · effort: maxIntelligence estimate9.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7–9.5, low 7, medium 8, high 8.5, xhigh 9, max 9.5
  • GPT-6 Astraeffort: low to maxGPT-6 Astra · effort: lowIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Astra · effort: mediumIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Astra · effort: highIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Astra · effort: xhighIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Astra · effort: maxIntelligence estimate9.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7.5–9.5, low 7.5, medium 8.5, high 9, xhigh 9, max 9.5
  • Claude Fable 5.1effort: low to maxClaude Fable 5.1 · effort: lowIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Fable 5.1 · effort: mediumIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Fable 5.1 · effort: highIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Fable 5.1 · effort: xhighIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Fable 5.1 · effort: maxIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7–9, low 7, medium 8, high 8.5, xhigh 9, max 9
  • Claude Sonnet 5.5effort: low to maxClaude Sonnet 5.5 · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Sonnet 5.5 · effort: mediumIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Sonnet 5.5 · effort: highIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Sonnet 5.5 · effort: xhighIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Sonnet 5.5 · effort: maxIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5–9, low 5, medium 6, high 7, xhigh 8, max 9
  • Gemini 4 Argoneffort: low to highGemini 4 Argon · effort: lowIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 4 Argon · effort: mediumIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 4 Argon · effort: highIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7.5–9, low 7.5, medium 8, high 9
  • GPT-6.1 Soleffort: low to maxGPT-6.1 Sol · effort: lowIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6.1 Sol · effort: mediumIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6.1 Sol · effort: highIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6.1 Sol · effort: xhighIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6.1 Sol · effort: maxIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6–9, low 6, medium 7.5, high 8, xhigh 8.5, max 9
  • Claude Fable 5effort: low to maxClaude Fable 5 · effort: lowIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Fable 5 · effort: mediumIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Fable 5 · effort: highIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Fable 5 · effort: xhighIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Fable 5 · effort: maxIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5–8.5, low 6.5, medium 7.5, high 8, xhigh 8.5, max 8.5
  • Claude Opus 5effort: low to maxClaude Opus 5 · effort: lowIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Opus 5 · effort: mediumIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Opus 5 · effort: highIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Opus 5 · effort: xhighIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Opus 5 · effort: maxIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5–8, low 6.5, medium 7, high 7.5, xhigh 8, max 8
  • GPT 5.6 Soleffort: none to maxGPT 5.6 Sol · effort: noneIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Sol · effort: lowIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Sol · effort: mediumIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Sol · effort: highIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Sol · effort: xhighIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Sol · effort: maxIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5–8, none 4.5, low 5.5, medium 6.5, high 7.5, xhigh 8, max 8
  • GPT-6 Soleffort: none to maxGPT-6 Sol · effort: noneIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Sol · effort: lowIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Sol · effort: mediumIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Sol · effort: highIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Sol · effort: xhighIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Sol · effort: maxIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5–8, none 4.5, low 5.5, medium 6.5, high 7.5, xhigh 8, max 8
  • GPT-6.1 Terraeffort: none to maxGPT-6.1 Terra · effort: noneIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6.1 Terra · effort: lowIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6.1 Terra · effort: mediumIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6.1 Terra · effort: highIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6.1 Terra · effort: xhighIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6.1 Terra · effort: maxIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4–7.5, none 4, low 4.5, medium 5.5, high 6, xhigh 6.5, max 7.5
  • Grok 4.7effort: low to xhighGrok 4.7 · effort: lowIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Grok 4.7 · effort: mediumIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Grok 4.7 · effort: highIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Grok 4.7 · effort: xhighIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6–7.5, low 6, medium 6.5, high 7, xhigh 7.5
  • Kimi K3.1 Prono effort settingKimi K3.1 Pro · no effort settingIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7.5, no effort setting 7.5
  • Kimi K3no effort settingKimi K3 · no effort settingIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7, no effort setting 7
  • Muse Wonder 1.0no effort settingMuse Wonder 1.0 · no effort settingIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7, no effort setting 7
  • Claude Haiku 5.5effort: low to maxClaude Haiku 5.5 · effort: lowIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Haiku 5.5 · effort: mediumIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Haiku 5.5 · effort: highIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Haiku 5.5 · effort: xhighIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Haiku 5.5 · effort: maxIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4–6.5, low 4, medium 5, high 5.5, xhigh 6, max 6.5
  • DeepSeek V4.1 Flash 1017effort: none to maxDeepSeek V4.1 Flash 1017 · effort: noneIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.DeepSeek V4.1 Flash 1017 · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.DeepSeek V4.1 Flash 1017 · effort: highIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.DeepSeek V4.1 Flash 1017 · effort: maxIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5–6.5, none 4.5, low 5, high 6, max 6.5
  • Gemini 3.7 Flasheffort: low to highGemini 3.7 Flash · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.7 Flash · effort: mediumIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.7 Flash · effort: highIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5–6.5, low 5, medium 5.5, high 6.5
  • Gemini 3.8 Flasheffort: low to highGemini 3.8 Flash · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.8 Flash · effort: mediumIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.8 Flash · effort: highIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5–6.5, low 5, medium 6, high 6.5
  • GLM 5.3effort: low to maxGLM 5.3 · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GLM 5.3 · effort: highIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GLM 5.3 · effort: maxIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5–6.5, low 5, high 6, max 6.5
  • GPT 5.6 Terraeffort: none to maxGPT 5.6 Terra · effort: noneIntelligence estimate3.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Terra · effort: lowIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Terra · effort: mediumIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Terra · effort: highIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Terra · effort: xhighIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Terra · effort: maxIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.3.5–6.5, none 3.5, low 4, medium 5, high 6, xhigh 6.5, max 6.5
  • Grok 4.6effort: low to xhighGrok 4.6 · effort: lowIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Grok 4.6 · effort: mediumIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Grok 4.6 · effort: highIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Grok 4.6 · effort: xhighIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5–6.5, low 5.5, medium 6, high 6.5, xhigh 6.5
  • Muse Spark 1.3no effort settingMuse Spark 1.3 · no effort settingIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5, no effort setting 6.5
  • Claude Sonnet 5effort: low to maxClaude Sonnet 5 · effort: lowIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Sonnet 5 · effort: mediumIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Sonnet 5 · effort: highIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Claude Sonnet 5 · effort: maxIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4–6, low 4, medium 4.5, high 5, max 6
  • DeepSeek V4.1 Flasheffort: none to maxDeepSeek V4.1 Flash · effort: noneIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.DeepSeek V4.1 Flash · effort: lowIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.DeepSeek V4.1 Flash · effort: highIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.DeepSeek V4.1 Flash · effort: maxIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4–6, none 4, low 4.5, high 5.5, max 6
  • Gemini 3.5 Flasheffort: minimal to highGemini 3.5 Flash · effort: minimalIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.5 Flash · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.5 Flash · effort: mediumIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.5 Flash · effort: highIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4–6, minimal 4, low 5, medium 5.5, high 6
  • GLM 5.3 Flasheffort: low to maxGLM 5.3 Flash · effort: lowIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GLM 5.3 Flash · effort: highIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GLM 5.3 Flash · effort: maxIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5–6, low 4.5, high 5.5, max 6
  • Grok 4.5effort: low to highGrok 4.5 · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Grok 4.5 · effort: mediumIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Grok 4.5 · effort: highIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5–6, low 5, medium 5.5, high 6
  • Muse Ember 1.0no effort settingMuse Ember 1.0 · no effort settingIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6, no effort setting 6
  • Muse Spark 1.2no effort settingMuse Spark 1.2 · no effort settingIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6, no effort setting 6
  • Gemini 3.6 Flasheffort: minimal to highGemini 3.6 Flash · effort: minimalIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.6 Flash · effort: lowIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.6 Flash · effort: mediumIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.6 Flash · effort: highIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4–5.5, minimal 4, low 4.5, medium 5, high 5.5
  • GPT 5.3 Codexeffort: low to xhighGPT 5.3 Codex · effort: lowIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.3 Codex · effort: mediumIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.3 Codex · effort: highIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.3 Codex · effort: xhighIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4–5.5, low 4, medium 4.5, high 5, xhigh 5.5
  • GPT-6 Lunaeffort: none to maxGPT-6 Luna · effort: noneIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Luna · effort: lowIntelligence estimate3 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Luna · effort: mediumIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Luna · effort: highIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Luna · effort: xhighIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT-6 Luna · effort: maxIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2.5–5.5, none 2.5, low 3, medium 4, high 4.5, xhigh 5, max 5.5
  • Muse Spark 1.1no effort settingMuse Spark 1.1 · no effort settingIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5, no effort setting 5.5
  • Qwen3.8-2.4T-A95Beffort: low to xhighQwen3.8-2.4T-A95B · effort: lowIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Qwen3.8-2.4T-A95B · effort: mediumIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Qwen3.8-2.4T-A95B · effort: xhighIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5–5.5, low 4.5, medium 5, xhigh 5.5
  • Gemini 3.1 Pro Previeweffort: low to highGemini 3.1 Pro Preview · effort: lowIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.1 Pro Preview · effort: mediumIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.1 Pro Preview · effort: highIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4–5, low 4, medium 4.5, high 5
  • GPT 5.6 Lunaeffort: none to maxGPT 5.6 Luna · effort: noneIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Luna · effort: lowIntelligence estimate3.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Luna · effort: mediumIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Luna · effort: highIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Luna · effort: xhighIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.6 Luna · effort: maxIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2.5–5, none 2.5, low 3.5, medium 4, high 4.5, xhigh 5, max 5
  • Gemini 3 Flash Previeweffort: minimal to highGemini 3 Flash Preview · effort: minimalIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3 Flash Preview · effort: lowIntelligence estimate3 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3 Flash Preview · effort: mediumIntelligence estimate3.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3 Flash Preview · effort: highIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2.5–4, minimal 2.5, low 3, medium 3.5, high 4
  • GPT 5.4 Minieffort: none to xhighGPT 5.4 Mini · effort: noneIntelligence estimate2 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.4 Mini · effort: lowIntelligence estimate3 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.4 Mini · effort: mediumIntelligence estimate3.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.4 Mini · effort: highIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.4 Mini · effort: xhighIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2–4, none 2, low 3, medium 3.5, high 4, xhigh 4
  • MindsHub Aireffort: none to mediumMindsHub Air · effort: noneIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.MindsHub Air · effort: lowIntelligence estimate3 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.MindsHub Air · effort: mediumIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2.5–4, none 2.5, low 3, medium 4
  • MindsHub Blazeeffort: none to highMindsHub Blaze · effort: noneIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.MindsHub Blaze · effort: highIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2.5–4, none 2.5, high 4
  • GPT 5.4 Nanoeffort: none to xhighGPT 5.4 Nano · effort: noneIntelligence estimate1.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.4 Nano · effort: lowIntelligence estimate2 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.4 Nano · effort: mediumIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.4 Nano · effort: highIntelligence estimate3 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.GPT 5.4 Nano · effort: xhighIntelligence estimate3 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.1.5–3, none 1.5, low 2, medium 2.5, high 3, xhigh 3
  • Gemini 3.1 Flash-Liteeffort: minimal to highGemini 3.1 Flash-Lite · effort: minimalIntelligence estimate1.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.1 Flash-Lite · effort: lowIntelligence estimate2 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.1 Flash-Lite · effort: mediumIntelligence estimate2 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.Gemini 3.1 Flash-Lite · effort: highIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.1.5–2.5, minimal 1.5, low 2, medium 2, high 2.5
  • Claude Haiku 4.5no effort settingClaude Haiku 4.5 · no effort settingIntelligence estimate2 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2, no effort setting 2
  • GPT-OSS 120B (Fireworks)no effort settingGPT-OSS 120B (Fireworks) · no effort settingIntelligence estimate2 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2, no effort setting 2
    • Claude Fable 5.2effort: lowClaude Fable 5.2 · effort: lowIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8.5
    • Claude Fable 5.2, effort: mediumClaude Fable 5.2 · effort: mediumIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.9
    • Claude Fable 5.2, effort: highClaude Fable 5.2 · effort: highIntelligence estimate9.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.9.5
    • Claude Fable 5.2, effort: xhighClaude Fable 5.2 · effort: xhighIntelligence estimate9.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.9.5
    • Claude Fable 5.2, effort: maxClaude Fable 5.2 · effort: maxIntelligence estimate10 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.10
    • Claude Opus 5.5effort: lowClaude Opus 5.5 · effort: lowIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7
    • Claude Opus 5.5, effort: mediumClaude Opus 5.5 · effort: mediumIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8
    • Claude Opus 5.5, effort: highClaude Opus 5.5 · effort: highIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8.5
    • Claude Opus 5.5, effort: xhighClaude Opus 5.5 · effort: xhighIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.9
    • Claude Opus 5.5, effort: maxClaude Opus 5.5 · effort: maxIntelligence estimate9.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.9.5
    • GPT-6 Astraeffort: lowGPT-6 Astra · effort: lowIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7.5
    • GPT-6 Astra, effort: mediumGPT-6 Astra · effort: mediumIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8.5
    • GPT-6 Astra, effort: highGPT-6 Astra · effort: highIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.9
    • GPT-6 Astra, effort: xhighGPT-6 Astra · effort: xhighIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.9
    • GPT-6 Astra, effort: maxGPT-6 Astra · effort: maxIntelligence estimate9.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.9.5
    • Claude Fable 5.1effort: lowClaude Fable 5.1 · effort: lowIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7
    • Claude Fable 5.1, effort: mediumClaude Fable 5.1 · effort: mediumIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8
    • Claude Fable 5.1, effort: highClaude Fable 5.1 · effort: highIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8.5
    • Claude Fable 5.1, effort: xhighClaude Fable 5.1 · effort: xhighIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.9
    • Claude Fable 5.1, effort: maxClaude Fable 5.1 · effort: maxIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.9
    • Claude Sonnet 5.5effort: lowClaude Sonnet 5.5 · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • Claude Sonnet 5.5, effort: mediumClaude Sonnet 5.5 · effort: mediumIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • Claude Sonnet 5.5, effort: highClaude Sonnet 5.5 · effort: highIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7
    • Claude Sonnet 5.5, effort: xhighClaude Sonnet 5.5 · effort: xhighIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8
    • Claude Sonnet 5.5, effort: maxClaude Sonnet 5.5 · effort: maxIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.9
    • Gemini 4 Argoneffort: lowGemini 4 Argon · effort: lowIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7.5
    • Gemini 4 Argon, effort: mediumGemini 4 Argon · effort: mediumIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8
    • Gemini 4 Argon, effort: highGemini 4 Argon · effort: highIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.9
    • GPT-6.1 Soleffort: lowGPT-6.1 Sol · effort: lowIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • GPT-6.1 Sol, effort: mediumGPT-6.1 Sol · effort: mediumIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7.5
    • GPT-6.1 Sol, effort: highGPT-6.1 Sol · effort: highIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8
    • GPT-6.1 Sol, effort: xhighGPT-6.1 Sol · effort: xhighIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8.5
    • GPT-6.1 Sol, effort: maxGPT-6.1 Sol · effort: maxIntelligence estimate9 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.9
    • Claude Fable 5effort: lowClaude Fable 5 · effort: lowIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • Claude Fable 5, effort: mediumClaude Fable 5 · effort: mediumIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7.5
    • Claude Fable 5, effort: highClaude Fable 5 · effort: highIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8
    • Claude Fable 5, effort: xhighClaude Fable 5 · effort: xhighIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8.5
    • Claude Fable 5, effort: maxClaude Fable 5 · effort: maxIntelligence estimate8.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8.5
    • Claude Opus 5effort: lowClaude Opus 5 · effort: lowIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • Claude Opus 5, effort: mediumClaude Opus 5 · effort: mediumIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7
    • Claude Opus 5, effort: highClaude Opus 5 · effort: highIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7.5
    • Claude Opus 5, effort: xhighClaude Opus 5 · effort: xhighIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8
    • Claude Opus 5, effort: maxClaude Opus 5 · effort: maxIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8
    • GPT 5.6 Soleffort: noneGPT 5.6 Sol · effort: noneIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5
    • GPT 5.6 Sol, effort: lowGPT 5.6 Sol · effort: lowIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • GPT 5.6 Sol, effort: mediumGPT 5.6 Sol · effort: mediumIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • GPT 5.6 Sol, effort: highGPT 5.6 Sol · effort: highIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7.5
    • GPT 5.6 Sol, effort: xhighGPT 5.6 Sol · effort: xhighIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8
    • GPT 5.6 Sol, effort: maxGPT 5.6 Sol · effort: maxIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8
    • GPT-6 Soleffort: noneGPT-6 Sol · effort: noneIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5
    • GPT-6 Sol, effort: lowGPT-6 Sol · effort: lowIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • GPT-6 Sol, effort: mediumGPT-6 Sol · effort: mediumIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • GPT-6 Sol, effort: highGPT-6 Sol · effort: highIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7.5
    • GPT-6 Sol, effort: xhighGPT-6 Sol · effort: xhighIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8
    • GPT-6 Sol, effort: maxGPT-6 Sol · effort: maxIntelligence estimate8 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.8
    • GPT-6.1 Terraeffort: noneGPT-6.1 Terra · effort: noneIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • GPT-6.1 Terra, effort: lowGPT-6.1 Terra · effort: lowIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5
    • GPT-6.1 Terra, effort: mediumGPT-6.1 Terra · effort: mediumIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • GPT-6.1 Terra, effort: highGPT-6.1 Terra · effort: highIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • GPT-6.1 Terra, effort: xhighGPT-6.1 Terra · effort: xhighIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • GPT-6.1 Terra, effort: maxGPT-6.1 Terra · effort: maxIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7.5
    • Grok 4.7effort: lowGrok 4.7 · effort: lowIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • Grok 4.7, effort: mediumGrok 4.7 · effort: mediumIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • Grok 4.7, effort: highGrok 4.7 · effort: highIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7
    • Grok 4.7, effort: xhighGrok 4.7 · effort: xhighIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7.5
    • Kimi K3.1 Prono effort settingKimi K3.1 Pro · no effort settingIntelligence estimate7.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7.5
    • Kimi K3no effort settingKimi K3 · no effort settingIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7
    • Muse Wonder 1.0no effort settingMuse Wonder 1.0 · no effort settingIntelligence estimate7 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.7
    • Claude Haiku 5.5effort: lowClaude Haiku 5.5 · effort: lowIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • Claude Haiku 5.5, effort: mediumClaude Haiku 5.5 · effort: mediumIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • Claude Haiku 5.5, effort: highClaude Haiku 5.5 · effort: highIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • Claude Haiku 5.5, effort: xhighClaude Haiku 5.5 · effort: xhighIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • Claude Haiku 5.5, effort: maxClaude Haiku 5.5 · effort: maxIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • DeepSeek V4.1 Flash 1017effort: noneDeepSeek V4.1 Flash 1017 · effort: noneIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5
    • DeepSeek V4.1 Flash 1017, effort: lowDeepSeek V4.1 Flash 1017 · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • DeepSeek V4.1 Flash 1017, effort: highDeepSeek V4.1 Flash 1017 · effort: highIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • DeepSeek V4.1 Flash 1017, effort: maxDeepSeek V4.1 Flash 1017 · effort: maxIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • Gemini 3.7 Flasheffort: lowGemini 3.7 Flash · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • Gemini 3.7 Flash, effort: mediumGemini 3.7 Flash · effort: mediumIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • Gemini 3.7 Flash, effort: highGemini 3.7 Flash · effort: highIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • Gemini 3.8 Flasheffort: lowGemini 3.8 Flash · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • Gemini 3.8 Flash, effort: mediumGemini 3.8 Flash · effort: mediumIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • Gemini 3.8 Flash, effort: highGemini 3.8 Flash · effort: highIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • GLM 5.3effort: lowGLM 5.3 · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • GLM 5.3, effort: highGLM 5.3 · effort: highIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • GLM 5.3, effort: maxGLM 5.3 · effort: maxIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • GPT 5.6 Terraeffort: noneGPT 5.6 Terra · effort: noneIntelligence estimate3.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.3.5
    • GPT 5.6 Terra, effort: lowGPT 5.6 Terra · effort: lowIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • GPT 5.6 Terra, effort: mediumGPT 5.6 Terra · effort: mediumIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • GPT 5.6 Terra, effort: highGPT 5.6 Terra · effort: highIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • GPT 5.6 Terra, effort: xhighGPT 5.6 Terra · effort: xhighIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • GPT 5.6 Terra, effort: maxGPT 5.6 Terra · effort: maxIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • Grok 4.6effort: lowGrok 4.6 · effort: lowIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • Grok 4.6, effort: mediumGrok 4.6 · effort: mediumIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • Grok 4.6, effort: highGrok 4.6 · effort: highIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • Grok 4.6, effort: xhighGrok 4.6 · effort: xhighIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • Muse Spark 1.3no effort settingMuse Spark 1.3 · no effort settingIntelligence estimate6.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6.5
    • Claude Sonnet 5effort: lowClaude Sonnet 5 · effort: lowIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • Claude Sonnet 5, effort: mediumClaude Sonnet 5 · effort: mediumIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5
    • Claude Sonnet 5, effort: highClaude Sonnet 5 · effort: highIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • Claude Sonnet 5, effort: maxClaude Sonnet 5 · effort: maxIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • DeepSeek V4.1 Flasheffort: noneDeepSeek V4.1 Flash · effort: noneIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • DeepSeek V4.1 Flash, effort: lowDeepSeek V4.1 Flash · effort: lowIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5
    • DeepSeek V4.1 Flash, effort: highDeepSeek V4.1 Flash · effort: highIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • DeepSeek V4.1 Flash, effort: maxDeepSeek V4.1 Flash · effort: maxIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • Gemini 3.5 Flasheffort: minimalGemini 3.5 Flash · effort: minimalIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • Gemini 3.5 Flash, effort: lowGemini 3.5 Flash · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • Gemini 3.5 Flash, effort: mediumGemini 3.5 Flash · effort: mediumIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • Gemini 3.5 Flash, effort: highGemini 3.5 Flash · effort: highIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • GLM 5.3 Flasheffort: lowGLM 5.3 Flash · effort: lowIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5
    • GLM 5.3 Flash, effort: highGLM 5.3 Flash · effort: highIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • GLM 5.3 Flash, effort: maxGLM 5.3 Flash · effort: maxIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • Grok 4.5effort: lowGrok 4.5 · effort: lowIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • Grok 4.5, effort: mediumGrok 4.5 · effort: mediumIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • Grok 4.5, effort: highGrok 4.5 · effort: highIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • Muse Ember 1.0no effort settingMuse Ember 1.0 · no effort settingIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • Muse Spark 1.2no effort settingMuse Spark 1.2 · no effort settingIntelligence estimate6 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.6
    • Gemini 3.6 Flasheffort: minimalGemini 3.6 Flash · effort: minimalIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • Gemini 3.6 Flash, effort: lowGemini 3.6 Flash · effort: lowIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5
    • Gemini 3.6 Flash, effort: mediumGemini 3.6 Flash · effort: mediumIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • Gemini 3.6 Flash, effort: highGemini 3.6 Flash · effort: highIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • GPT 5.3 Codexeffort: lowGPT 5.3 Codex · effort: lowIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • GPT 5.3 Codex, effort: mediumGPT 5.3 Codex · effort: mediumIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5
    • GPT 5.3 Codex, effort: highGPT 5.3 Codex · effort: highIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • GPT 5.3 Codex, effort: xhighGPT 5.3 Codex · effort: xhighIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • GPT-6 Lunaeffort: noneGPT-6 Luna · effort: noneIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2.5
    • GPT-6 Luna, effort: lowGPT-6 Luna · effort: lowIntelligence estimate3 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.3
    • GPT-6 Luna, effort: mediumGPT-6 Luna · effort: mediumIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • GPT-6 Luna, effort: highGPT-6 Luna · effort: highIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5
    • GPT-6 Luna, effort: xhighGPT-6 Luna · effort: xhighIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • GPT-6 Luna, effort: maxGPT-6 Luna · effort: maxIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • Muse Spark 1.1no effort settingMuse Spark 1.1 · no effort settingIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • Qwen3.8-2.4T-A95Beffort: lowQwen3.8-2.4T-A95B · effort: lowIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5
    • Qwen3.8-2.4T-A95B, effort: mediumQwen3.8-2.4T-A95B · effort: mediumIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • Qwen3.8-2.4T-A95B, effort: xhighQwen3.8-2.4T-A95B · effort: xhighIntelligence estimate5.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5.5
    • Gemini 3.1 Pro Previeweffort: lowGemini 3.1 Pro Preview · effort: lowIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • Gemini 3.1 Pro Preview, effort: mediumGemini 3.1 Pro Preview · effort: mediumIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5
    • Gemini 3.1 Pro Preview, effort: highGemini 3.1 Pro Preview · effort: highIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • GPT 5.6 Lunaeffort: noneGPT 5.6 Luna · effort: noneIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2.5
    • GPT 5.6 Luna, effort: lowGPT 5.6 Luna · effort: lowIntelligence estimate3.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.3.5
    • GPT 5.6 Luna, effort: mediumGPT 5.6 Luna · effort: mediumIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • GPT 5.6 Luna, effort: highGPT 5.6 Luna · effort: highIntelligence estimate4.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4.5
    • GPT 5.6 Luna, effort: xhighGPT 5.6 Luna · effort: xhighIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • GPT 5.6 Luna, effort: maxGPT 5.6 Luna · effort: maxIntelligence estimate5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.5
    • Gemini 3 Flash Previeweffort: minimalGemini 3 Flash Preview · effort: minimalIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2.5
    • Gemini 3 Flash Preview, effort: lowGemini 3 Flash Preview · effort: lowIntelligence estimate3 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.3
    • Gemini 3 Flash Preview, effort: mediumGemini 3 Flash Preview · effort: mediumIntelligence estimate3.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.3.5
    • Gemini 3 Flash Preview, effort: highGemini 3 Flash Preview · effort: highIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • GPT 5.4 Minieffort: noneGPT 5.4 Mini · effort: noneIntelligence estimate2 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2
    • GPT 5.4 Mini, effort: lowGPT 5.4 Mini · effort: lowIntelligence estimate3 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.3
    • GPT 5.4 Mini, effort: mediumGPT 5.4 Mini · effort: mediumIntelligence estimate3.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.3.5
    • GPT 5.4 Mini, effort: highGPT 5.4 Mini · effort: highIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • GPT 5.4 Mini, effort: xhighGPT 5.4 Mini · effort: xhighIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • MindsHub Aireffort: noneMindsHub Air · effort: noneIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2.5
    • MindsHub Air, effort: lowMindsHub Air · effort: lowIntelligence estimate3 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.3
    • MindsHub Air, effort: mediumMindsHub Air · effort: mediumIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • MindsHub Blazeeffort: noneMindsHub Blaze · effort: noneIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2.5
    • MindsHub Blaze, effort: highMindsHub Blaze · effort: highIntelligence estimate4 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.4
    • GPT 5.4 Nanoeffort: noneGPT 5.4 Nano · effort: noneIntelligence estimate1.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.1.5
    • GPT 5.4 Nano, effort: lowGPT 5.4 Nano · effort: lowIntelligence estimate2 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2
    • GPT 5.4 Nano, effort: mediumGPT 5.4 Nano · effort: mediumIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2.5
    • GPT 5.4 Nano, effort: highGPT 5.4 Nano · effort: highIntelligence estimate3 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.3
    • GPT 5.4 Nano, effort: xhighGPT 5.4 Nano · effort: xhighIntelligence estimate3 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.3
    • Gemini 3.1 Flash-Liteeffort: minimalGemini 3.1 Flash-Lite · effort: minimalIntelligence estimate1.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.1.5
    • Gemini 3.1 Flash-Lite, effort: lowGemini 3.1 Flash-Lite · effort: lowIntelligence estimate2 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2
    • Gemini 3.1 Flash-Lite, effort: mediumGemini 3.1 Flash-Lite · effort: mediumIntelligence estimate2 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2
    • Gemini 3.1 Flash-Lite, effort: highGemini 3.1 Flash-Lite · effort: highIntelligence estimate2.5 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2.5
    • Claude Haiku 4.5no effort settingClaude Haiku 4.5 · no effort settingIntelligence estimate2 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2
    • GPT-OSS 120B (Fireworks)no effort settingGPT-OSS 120B (Fireworks) · no effort settingIntelligence estimate2 / 10MindsHub’s subjective assessment of public benchmarks and rankings. Results depend on your task.2

Bar: score range. Dot: effort level. Ring: selected effort.

About the data

What does this page show?

Performance and reliability measured through MindsHub Inference, alongside current token prices, API aliases and fallback routes. The figures describe the models as served through MindsHub. They are not a ranking of every provider’s deployment of those models.

Where do the measurements come from?

We run automated API checks and writing tasks through MindsHub Inference. Complex task, writing speed and cost per task figures refresh every two hours, and the other measurements every six hours. Complex task performance and cost cover up to 35 days of tests. Each chart shows its measurement dates. If an update fails, we keep previously saved measurements with their original dates. Prices, aliases and fallback routes come from the same live catalog as our pricing page. A dash means no usable measurement is available.

How is Ping measured?

Every 10 minutes, checks from multiple regions ask for a one-word reply at the lowest reasoning effort. We time the first answer token, including any thinking before it. Ping measures basic responsiveness and tracks availability.

Sample prompt

Reply with the single word: ok
How is the Simple task measured?

Every six hours, the model receives a short briefing about a fictional market hall and is asked to describe a Saturday morning in at least 150 words. It must interpret the facts, decide how to present them and follow the writing constraints. We time the first answer token at the default reasoning effort, including thinking time.

Sample prompt, abridged; briefing omitted

Using only the supplied market-hall briefing, describe a typical Saturday morning in at least 150 words. Use plain paragraphs, with no headings or lists, and do not add facts.
How is the Complex task measured?

The model receives a longer briefing about the same fictional market hall and must turn it into a complete visitor’s guide of at least 800 words. It must analyze and organize the supplied facts, cover them in order and obey content and formatting constraints. We measure the first answer token, total response time and writing speed at each tested effort level. The first-answer and total times include thinking; writing speed starts when the answer begins. Repeated tests run over several weeks; each model’s details show the test count and interval. These are speed tests, not scores for reasoning quality.

Sample prompt, abridged; briefing omitted

Using only the supplied briefing, write a visitor’s guide of at least 800 words. Cover every part in the given order, in plain paragraphs with no headings, lists or tables. Do not add facts.
What are p50, p05 and p95?

P50 is the median: half of measurements are at or below it and half at or above it. P05 and P95 mark the lower and upper ends of the middle 90% of measurements. The leaderboard shows p50. Open Performance to explore the spread; Ping and Simple task have p50 and p95 only.

Does availability below 100% mean requests failed?

Not necessarily. A configured fallback route can still answer when the model you chose does not. Availability before fallback is the share of our automated checks answered by that model, including retries, over the selected period. Other checks were answered by a fallback or got no answer. These checks do not measure how often customer requests fail. Failures attributed to our monitoring network are excluded.

What does the intelligence score mean?

MindsHub’s read is a subjective estimate from 1 to 10 based on public benchmarks and rankings, not a precise measurement. Performance depends on your workload; test models on your own tasks.

For detailed benchmarks, refer to third party services such as Artificial Analysis, Epoch AI or similar.

How is cost per task compared?

The most expensive measured model and effort level is the 100% reference, updated automatically as results change. The leaderboard range covers a model’s measured effort levels; expand it for individual values. In Cost per task, choose another reference to compare against. Dollar estimates use mean input and output tokens at current standard rates, excluding cache discounts. Your bill depends on your requests.

What changes with reasoning effort?

Intelligence, Complex task timings and writing speed follow the selected effort. Ping always uses the lowest effort and Simple task the default. The cost range covers all measured levels. Views showing all effort levels disable the selector because every level is already visible.

What are fixed and rotating aliases?

An alias is the name sent in the API’s model field. Fixed aliases select a specific model version. Rotating aliases follow a model family as it updates. MindsHub Air and MindsHub Blaze are managed rotating aliases: MindsHub can change the model behind each name. The Aliases tab explains their purpose and lists the names you can use.

How do token prices, context limits and the free tier work?

Tokens are pieces of text. The context limit is how much input a model accepts in one request. Token prices are US dollars per million input or output tokens, from the same catalog as the pricing page. MindsHub Air is free within the free-tier limits; its listed token rates apply to usage beyond those limits. TypeSafe’s Jev is free. See Prices for cached-input, cache-write and other rates.

Which models are included?

The leaderboard covers chat models and their managed aliases. Other models lists decision and embedding models with their own response-time measurements and availability. See mindshub.ai/unified-inference#free-tier for the free tier and mindshub.ai/pricing for rates and credits.