MiniMax-M2.7

Composite indexes

• Artificial Analysis Intelligence Index#60 of 142
  23independentv4.3.2, reasoningArtificial Analysis: MiniMax-M2.7 ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 4.0#69 of 88
  0%independentreasoning, AA-runArtificial Analysis: MiniMax-M2.7 ↗

  Leader: Claude Mythos 5.1 at 60.9%

• Terminal-Bench 2.x#53 of 103
  55.4%independentTerminal-Bench 2.1, reasoning, AA-runArtificial Analysis: MiniMax-M2.7 ↗

  Leader: Claude Fable 5.1 at 91.4%

• SciCode#41 of 94
  50.1%independentreasoning, AA-runArtificial Analysis: MiniMax-M2.7 ↗

  Leader: Claude Opus 5.5 at 66.9%

Agents and tool use

• τ²-Bench#27 of 88
  84.8%independenttelecom, reasoning, AA-runArtificial Analysis: MiniMax-M2.7 ↗

  Leader: GLM-5.2 at 99.1%

• GDPval-AA#54 of 103
  999independentGDPval-AA v2.1, reasoningArtificial Analysis: MiniMax-M2.7 ↗

  Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

• GPQA Diamond#48 of 142
  87.4%independentreasoning, AA-runArtificial Analysis: MiniMax-M2.7 ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#56 of 147
  29.6%independentreasoning, no tools, AA-runArtificial Analysis: MiniMax-M2.7 ↗

  Leader: Claude Opus 5.5 at 61.4%

• CritPt#75 of 139
  0.6%independentreasoning, AA-runArtificial Analysis: MiniMax-M2.7 ↗

  Leader: GPT-5.6 Sol at 32.3%

Vision and long context

• AA Long Context Reasoning#46 of 139
  78.3%independentreasoning, AA-LCRArtificial Analysis: MiniMax-M2.7 ↗

  Leader: Kimi K3 at 88.7%

Human preference

• LMArena Text#45 of 54
  1415independentarena entry "minimax-m2.7", 69,169 votes, checked 2026-09-25Arena (LMArena) text leaderboard ↗

  Leader: Claude Fable 5 at 1506

• LMArena WebDev#47 of 54
  1397independentarena entry "minimax-m2.7", 15,186 votes, checked 2026-09-25Arena (LMArena) WebDev/Code leaderboard ↗

  Leader: Claude Opus 5.5 at 1818

Other published results