benchgap
MiniMax · model

MiniMax M2.7 benchmark scores

As of 2026-11-22, MiniMax M2.7 (MiniMax) has measured scores on 37 benchmarks and estimated scores on 116 more.

BenchmarkScoreSource
AA-GPQA Diamond87.4%measured
AA-HLE29.6%measured
AA-SciCode50.1%measured
AIME2689.8%measured
Artificial Analysis Intelligence Index22.8%measured
CritPt0.6%measured
GDPval-AA25.5%measured
GPQA Diamond87.0%measured
HLE28.0%measured
IFBench74.0%estimated ± 6.6 pp, medium confidence
AA-LCR78.3%measured
LiveCodeBench v687.0%estimated ± 1.7 pp, high confidence
AA-Omniscience Accuracy26.8%measured
SciCode49.9%estimated ± 3.1 pp, high confidence
Terminal-Bench 2.159.2%estimated ± 6.7 pp, medium confidence
BrowseComp60.2%estimated ± 4.2 pp, medium confidence
HLE w/ tools35.4%estimated ± 4.1 pp, low confidence
IFEval93.0%estimated ± 2.8 pp, high confidence
LongBench v264.2%estimated ± 5.5 pp, medium confidence
VITA-Bench28.2%estimated ± 10.7 pp, low confidence
τ²-bench results84.8%measured
AA Coding Index52.6%measured
APEX-Agents18.5%estimated ± 9.4 pp, low confidence
APEX-Agents-AA10.6%measured
BioMysteryBench (human-difficult)11.6%estimated ± 6.8 pp, low confidence
DeepSearchQA81.8%estimated ± 4.5 pp, high confidence
SWE-bench Verified78.6%estimated ± 2.3 pp, high confidence
AutomationBench48.4%estimated ± 9.1 pp, low confidence
BFCL v473.5%estimated ± 2.7 pp, high confidence
CyberGym58.5%estimated ± 5.3 pp, low confidence
JobBench34.1%estimated ± 7.3 pp, low confidence
SWE-bench Pro56.2%measured
τ³-bench results67.6%measured
WideResearch70.0%estimated ± 3.3 pp, high confidence
AA Agentic Index16.8%measured
MMLU-Pro82.2%estimated ± 4.8 pp, high confidence
AA-IFBench75.7%measured
FailureSensorIQ63.2%estimated ± 1.7 pp, high confidence
GPQA86.9%estimated ± 1.2 pp, high confidence
MMLU90.5%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond86.6%measured
Vals LiveCodeBench79.9%measured
Vals MMLU-Pro80.4%measured
MATH-50096.9%estimated ± 3.1 pp, medium confidence
MMMLU85.9%estimated ± 0.7 pp, medium confidence
Chess Puzzles19.3%estimated ± 12.3 pp, low confidence
AIME 202590.7%estimated ± 1.8 pp, medium confidence
AA MMLU-Pro85.4%estimated ± 0.7 pp, high confidence
Gert Labs28.8%measured
AA Harvey LAB v1.080.0%estimated ± 1.2 pp, low confidence
AA Tau3 Banking39.6%estimated ± 2.0 pp, low confidence
AA Terminal-Bench 2.179.6%estimated ± 2.5 pp, medium confidence
ApprenticeBench3.2%estimated ± 10.4 pp, low confidence
ARC-AGI-184.4%estimated ± 2.5 pp, medium confidence
ARC-AGI-240.6%estimated ± 9.7 pp, low confidence
CursorBench 3.144.3%estimated ± 3.4 pp, low confidence
CursorBench 3.252.5%estimated ± 3.6 pp, high confidence
EBR-bench0.0%estimated ± 9.1 pp, low confidence
FrontierCode 1.1 Main11.6%estimated ± 4.3 pp, low confidence
FrontierMath v2 (Tiers 1-3)9.6%estimated ± 8.8 pp, low confidence
FrontierSWE v29.0%estimated ± 8.3 pp, medium confidence
MazeBench0.0%estimated ± 2.7 pp, high confidence
Mystery Game Puzzles12.8%estimated ± 9.8 pp, low confidence
NYT Connections24.7%measured
OSWorld-Verified57.9%estimated ± 3.8 pp, low confidence
Terminal-Bench 4.17.4%estimated ± 14.9 pp, low confidence
Terminal-Bench Hard44.7%estimated ± 3.9 pp, medium confidence
Vals SWE-bench73.8%measured
Terminal-Bench 2.1 (Vals AI)48.7%measured
VulcanBench v380.9%estimated ± 5.6 pp, low confidence
CWE-Bench-AA39.1%estimated ± 8.1 pp, medium confidence
AA Cyber Index11.5%estimated ± 9.2 pp, low confidence
DeepsecBench-AA8.7%estimated ± 8.2 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)52.7%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)57.7%estimated ± 1.1 pp, low confidence
AA ITBench38.2%estimated ± 4.0 pp, high confidence
Bug Hunt Bench10.4%estimated ± 7.2 pp, low confidence
CursorBench 4.032.7%estimated ± 3.3 pp, medium confidence
CWE-bench v138.5%estimated ± 5.7 pp, medium confidence
DeepSWE56.3%estimated ± 7.2 pp, low confidence
DRACO72.9%estimated ± 2.0 pp, medium confidence
FrontierCode 2.020.1%estimated ± 6.7 pp, low confidence
HLE w/o tools32.5%estimated ± 2.7 pp, high confidence
OSWorld 2.19.3%estimated ± 3.6 pp, medium confidence
OSWorld 2.1 Offline2.7%estimated ± 1.9 pp, low confidence
PostTrainBench v1.118.7%estimated ± 3.7 pp, medium confidence
StealthMark41.3%estimated ± 10.7 pp, low confidence
SWE Multilingual76.5%measured
Toolathlon-Verified43.3%estimated ± 2.3 pp, low confidence
VulcanBench Frontier v480.3%estimated ± 6.8 pp, low confidence
AA AutomationBench42.6%estimated ± 9.9 pp, low confidence
GDP.pdf13.0%estimated ± 4.2 pp, medium confidence
AA Terminal-Bench 4.00.0%estimated ± 13.7 pp, low confidence
ARC-AGI-30.0%estimated ± 8.6 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
cursorBench4144.8%estimated ± 3.7 pp, medium confidence
CWE-bench32.4%estimated ± 6.2 pp, low confidence
MKA32.9%estimated ± 4.6 pp, medium confidence
SkillsBench official leaderboard (BenchFlow)34.9%measured
BinaryAudit19.6%estimated ± 12.0 pp, low confidence
OTelBench6.8%estimated ± 6.6 pp, medium confidence
Vibe Code Bench27.0%measured
FACTS Multimodal16.0%estimated ± 4.0 pp, medium confidence
Hermes Bench56.2%estimated ± 2.9 pp, high confidence
Hermes Index19.7%estimated ± 5.7 pp, low confidence
ExploitGym0.0%estimated ± 8.3 pp, low confidence
C-Eval92.7%estimated ± 0.9 pp, medium confidence
Claw-Eval48.7%measured
DeepPlanning30.4%estimated ± 8.3 pp, low confidence
HMMT Feb 202581.4%estimated ± 1.9 pp, high confidence
HMMT Feb 202672.7%measured
HMMT Nov 202581.0%measured
INCLUDE85.5%estimated ± 2.0 pp, medium confidence
MCP Atlas64.6%estimated ± 7.8 pp, low confidence
MCP-Tasks66.8%estimated ± 3.6 pp, medium confidence
MMAnswerBench74.2%estimated ± 1.3 pp, medium confidence
MMLU-ProX85.4%estimated ± 1.3 pp, high confidence
MMLU-Redux94.3%estimated ± 0.8 pp, medium confidence
NL2Repo39.8%measured
PostTrainBench v119.0%estimated ± 3.1 pp, medium confidence
QwenClawBench55.9%estimated ± 6.0 pp, low confidence
SuperGPQA68.6%estimated ± 7.2 pp, medium confidence
Terminal-Bench 2.057.0%measured
Toolathlon46.3%measured
AA LiveCodeBench88.3%estimated ± 2.6 pp, high confidence
HealthBench Hard6.5%estimated ± 8.6 pp, low confidence
LiveCodeBench Pro80.7%estimated ± 6.0 pp, low confidence
MedXpertQA (Text)45.9%estimated ± 4.5 pp, low confidence
MMLU-Pro (Arcee)80.8%measured
React Native Evals71.4%measured
ResearchClawBench13.5%estimated ± 1.3 pp, medium confidence
SWE-Rebench51.9%measured
PostTrainBench16.1%estimated ± 3.7 pp, medium confidence
Finance Agent v255.1%estimated ± 2.4 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
FrontierCode 1.1 Extended54.7%estimated ± 3.0 pp, low confidence
HealthBench (raw)38.5%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)49.6%estimated ± 3.4 pp, low confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)49.7%estimated ± 4.5 pp, medium confidence
HLE-Verified15.3%estimated ± 2.0 pp, low confidence
LABBench273.1%estimated ± 1.8 pp, low confidence
ScarfBench24.8%estimated ± 9.1 pp, low confidence
STEMBench2.4%estimated ± 0.2 pp, medium confidence
SimpleQA27.4%estimated ± 4.3 pp, medium confidence
Agents' Last Exam29.6%estimated ± 9.7 pp, low confidence
OpenHarmony Bench v1.054.5%estimated ± 2.4 pp, high confidence
IMOAnswerBench73.1%estimated ± 5.6 pp, medium confidence
MRCRv285.5%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.3%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
LifeVal5.5%estimated ± 5.0 pp, low confidence
PinchBench94.4%estimated ± 5.5 pp, low confidence