MiniMax-M2.1 places in the top three on Multi-SWE-bench.
MiniMax Dec 2025 Open weights Flagship
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMLU-Pro | 88% | #5 of 151 | Model card | |
| LMArena (Elo) | 1,385 | #148 of 333 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 57.8 | #69 of 119 | Official leaderboard | |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 62% | #19 of 31 | Model card | |
| IFBench | 70% | #43 of 70 | Model card | |
| Humanity's Last Exam | 22.2% | #92 of 147 | Model card | |
| Vectara Hallucination Leaderboard (2025 dataset) | 11.8% | #77 of 104 | Official leaderboard | |
| LOCA-Bench | 5.30% | #7 of 9 | Official leaderboard | |
| Extended NYT Connections | 11.2% | #91 of 97 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 83% | #92 of 284 | Model card | |
| AIME 2025 | 83% | #82 of 143 | Model card | |
| SimpleBench | 34.7% | #74 of 100 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveCodeBench | 81% | #10 of 73 | Model card | |
| Multi-SWE-bench | 49.4% | #3 of 10 | Model card | |
| LiveSQLBench | 28.7% | #12 of 36 | Official leaderboard | |
| SWE-bench Verified | 74% | #51 of 150 | Model card | |
| SWE-bench Multilingual | 72.5% | #36 of 70 | Model card | |
| SWE-Bench Pro | 36.8% | #14 of 24 | Official leaderboard | |
| SciCode | 41% | #28 of 47 | Model card | |
| WebDev Arena | 1,387 | #72 of 105 | Epoch AI | |
| Code Arena | 1,384 | #89 of 124 | Official leaderboard | |
| ALE-Bench | 624 | #90 of 121 | Epoch AI | |
| OpenHands Index | 41.2% | #27 of 33 | Official leaderboard | |
| PostTrainBench | 9.33% | #20 of 23 | Official leaderboard | |
| IOI (Vals) | 2.33% | #50 of 55 | Official leaderboard | |
| OctoCodingbench | 26.1% | #1 of 1 | Model card | |
| SWE-Perf | 3.10% | #1 of 1 | Model card | |
| SWE-Review | 8.90% | #1 of 1 | Model card | |
| SWT-bench | 69.3% | #1 of 1 | Model card | |
| VIBE (MiniMax) | 88.6% | #1 of 1 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| PinchBench | 80.4% | #5 of 48 | Official leaderboard | |
| tau2-bench | 87% | #21 of 69 | Model card | |
| Toolathlon | 40.7% | #17 of 50 | Official leaderboard | |
| Terminal-Bench 2.0 | 36.6% | #26 of 43 | Official leaderboard | |
| BrowseComp | 62% | #53 of 77 | Model card | |
| SnakeBench | 20 | #133 of 183 | Official leaderboard | |
| Pencil Puzzle Bench | 0% | #45 of 53 | Official leaderboard | |
| BalatroBench | 3.07 | #16 of 16 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vals Finance Agent v1 | 29.7% | #24 of 47 | Official leaderboard | |
| MedScribe | 80.8% | #51 of 98 | Official leaderboard | |
| CaseLaw v2 | 55.8% | #33 of 53 | Official leaderboard | |
| CorpFin v2 | 58.9% | #77 of 119 | Official leaderboard | |
| LegalBench | 75.5% | #106 of 138 | Official leaderboard | |
| MedCode | 34.1% | #76 of 96 | Official leaderboard | |
| TaxEval v2 | 66.3% | #103 of 129 | Official leaderboard | |
| ProfBench | 41.6% | #59 of 72 | Official leaderboard | |
| Vals Finance Agent | 33.4% | #43 of 49 | Official leaderboard |
The benchmarks the lab chose to headline, with the scores it gave.