Benchmarks

21 results across 13 benchmarks

Benchmark results for MiniMax M2.7
BenchmarkScoreSource
AutomationBench 1.0.6Effort: High0.5%zapier.com for MiniMax M2.7 (high) on AutomationBench 1.0.6 (opens in a new tab)Archived copy (opens in a new tab)Task pass rateReported Benchmark leaderboardZapierIndependentZapier AutomationBench TeamRecord for MiniMax M2.7 on AutomationBench 1.0.6
BrowseComp 130-question subset — Mercor web research agentEffort: HighConfiguration: Mercor web research agent, 100 steps, 3 hours38.3%mercor.com for MiniMax M2.7 (high) on BrowseComp 130-question subset — Mercor web research agent (opens in a new tab)Archived copy (opens in a new tab)BrowseComp AccuracyReported Benchmark leaderboardMercorIndependentRecord for MiniMax M2.7 on BrowseComp 130-question subset — Mercor web research agent
DeepSWE 1.1 — Mercor mini-swe-agent, 500 stepsEffort: HighConfiguration: Mercor mini-swe-agent, 500 steps, 2 hours0.0%mercor.com for MiniMax M2.7 (high) on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps (opens in a new tab)Archived copy (opens in a new tab)DeepSWE Pass@1Reported Benchmark leaderboardMercorIndependentRecord for MiniMax M2.7 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps
Finance Agent Benchmark 2 — October 2026 evaluation27.9%vals.ai for MiniMax M2.7 on Finance Agent Benchmark 2 — October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)Finance Agent AccuracyReported Benchmark leaderboardVals AIIndependentRecord for MiniMax M2.7 on Finance Agent Benchmark 2 — October 2026 evaluation
GPQA Diamond — Mercor single-shotEffort: HighConfiguration: Mercor single-shot agent86.0%mercor.com for MiniMax M2.7 (high) on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Benchmark leaderboardMercorIndependentRecord for MiniMax M2.7 on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot
GPQA Diamond — Vals AI harnessConfiguration: Vals AI harness: mean of zero-shot and few-shot CoT86.6%vals.ai for MiniMax M2.7 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Benchmark leaderboardVals AIIndependentRecord for MiniMax M2.7 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness
HLAB October 2026 evaluation0.0%vals.ai for MiniMax M2.7 on Harvey's Legal Agent Benchmark October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)HLAB Task Pass RateReported Benchmark leaderboardVals AIIndependentRecord for MiniMax M2.7 on Harvey's Legal Agent Benchmark October 2026 evaluation
Humanity's Last Exam Text only — Mercor single-shotEffort: HighConfiguration: Mercor single-shot agent27.1%mercor.com for MiniMax M2.7 (high) on Humanity's Last Exam Text only — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)Humanity's Last Exam AccuracyReported Benchmark leaderboardMercorIndependentRecord for MiniMax M2.7 on Humanity's Last Exam Text only — Mercor single-shot
MMLU-Pro Original — Mercor single-shotEffort: HighConfiguration: Mercor single-shot agent79.6%mercor.com for MiniMax M2.7 (high) on MMLU-Pro Original — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Benchmark leaderboardMercorIndependentRecord for MiniMax M2.7 on MMLU-Pro Original — Mercor single-shot
MMLU-Pro Original — Vals AI harnessConfiguration: Vals AI harness80.4%vals.ai for MiniMax M2.7 on MMLU-Pro Original — Vals AI harness (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Benchmark leaderboardVals AIIndependentRecord for MiniMax M2.7 on MMLU-Pro Original — Vals AI harness
SWE-bench Multilingual76.5%minimax.io for MiniMax M2.7 on SWE-bench Multilingual (opens in a new tab)Resolved TasksReported Launch postMiniMaxSelf-reportedRecord for MiniMax M2.7 on SWE-bench Multilingual
SWE-bench Multilingual — Mercor mini-swe-agent, 1000 stepsEffort: HighConfiguration: Mercor mini-swe-agent, 1000 steps, 3 hours60.8%mercor.com for MiniMax M2.7 (high) on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardMercorIndependentRecord for MiniMax M2.7 on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps
SWE-bench Verified — Mercor mini-swe-agent, 1000 stepsEffort: HighConfiguration: Mercor mini-swe-agent, 1000 steps, 3 hours75.3%mercor.com for MiniMax M2.7 (high) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardMercorIndependentRecord for MiniMax M2.7 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps
SWE-bench Verified — Vals AI mini-swe-agentConfiguration: mini-swe-agent harness73.8%vals.ai for MiniMax M2.7 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for MiniMax M2.7 on SWE-bench Verified — Vals AI mini-swe-agent
SWE-bench Pro Public56.2%minimax.io for MiniMax M2.7 on SWE-bench Pro Public (opens in a new tab)Public tasks resolvedReported Launch postMiniMaxSelf-reportedRecord for MiniMax M2.7 on SWE-bench Pro Public
Terminal-Bench 2.057.0%minimax.io for MiniMax M2.7 on Terminal-Bench 2.0 (opens in a new tab)Terminal-Bench AccuracyReported Launch postMiniMaxSelf-reportedRecord for MiniMax M2.7 on Terminal-Bench 2.0
Terminal-Bench 2.0 — Vals AI Terminus 2Configuration: Terminus-2 harness47.2%vals.ai for MiniMax M2.7 on Terminal-Bench 2.0 — Vals AI Terminus 2 (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardVals AIIndependentRecord for MiniMax M2.7 on Terminal-Bench 2.0 — Vals AI Terminus 2
Terminal-Bench 2.1 — Mercor Terminus 2Effort: HighConfiguration: Mercor Terminus 2, 1000 steps, 3 hours54.3%mercor.com for MiniMax M2.7 (high) on Terminal-Bench 2.1 — Mercor Terminus 2 (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardMercorIndependentRecord for MiniMax M2.7 on Terminal-Bench 2.1 — Mercor Terminus 2
Terminal-Bench 2.1 — Vals AI Terminus 2Configuration: Terminus-2 harness48.7%vals.ai for MiniMax M2.7 on Terminal-Bench 2.1 — Vals AI Terminus 2 (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardVals AIIndependentRecord for MiniMax M2.7 on Terminal-Bench 2.1 — Vals AI Terminus 2
Toolathlon Verified47.5%toolathlon.xyz for MiniMax M2.7 on Toolathlon Verified (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for MiniMax M2.7 on Toolathlon Verified
Vibe Code Bench 1.1 — OpenHands, October 2026 evaluationConfiguration: OpenHands harness11.9%vals.ai for MiniMax M2.7 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)Vibe Code Bench ScoreReported Benchmark leaderboardVals AIIndependentRecord for MiniMax M2.7 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation