MiMo-V2.5 places in the top three on 2 benchmarks.
Open weights
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 | |
|---|---|---|---|---|
| LMArena (Elo) | 1,434 | #87 of 333 | Official leaderboard | |
| BullshitBench | 30.9% | #49 of 107 | Official leaderboard | |
| Wer wird Millionär? LLM Benchmark | 9778.0 | #35 of 76 | Official leaderboard | |
| BullshitBench V2 | 35% | #63 of 122 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CritPt | 3.71% | #73 of 160 | Epoch AI | |
| ProofBench | 16% | #36 of 59 | Official leaderboard | |
| ResearchClawBench | 16.9 | #16 of 23 | Official leaderboard | |
| ProofBench v1.1 | 16% | #43 of 51 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WebDev Arena | 1,437 | #57 of 105 | Epoch AI | |
| Code Arena | 1,438 | #68 of 124 | Official leaderboard | |
| SWE-Bench Pro | 56.1% | #43 of 77 | Model card | |
| Vibe Code Bench | 42.2% | #67 of 115 | Official leaderboard | |
| Code Migration | 14.2% | #57 of 78 | Official leaderboard | |
| ALE-Bench | 514 | #99 of 121 | Epoch AI | |
| MiMo Coding Bench | 71.8% | #2 of 2 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| PinchBench 2.0 | 89.7% | #5 of 57 | Official leaderboard | |
| Terminal-Bench 2.0 | 65.8% | #13 of 61 | Model card | |
| Claw-Eval | 78.4% | #6 of 23 | Official leaderboard | |
| Claw-Eval Pass^3 | 62.3% | #8 of 23 | Official leaderboard | |
| SnakeBench | 21 | #112 of 183 | Official leaderboard | |
| Toolathlon-Verified | 49.1% | #20 of 25 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| TaxEval v2 | 71.8% | #69 of 129 | Official leaderboard | |
| CorpFin v2 | 59.9% | #70 of 119 | Official leaderboard | |
| Harvey LAB (Legal Agent Benchmark) | 1.67% | #51 of 80 | Official leaderboard | |
| Excel Modeling Benchmark | 55.1% | #50 of 76 | Official leaderboard | |
| LegalBench | 78.9% | #94 of 138 | Official leaderboard | |
| MortgageTax | 59.3% | #63 of 86 | Official leaderboard | |
| MedScribe | 72.2% | #82 of 98 | Official leaderboard | |
| Vals Finance Agent v2 | 36.7% | #68 of 80 | Official leaderboard | |
| Tax Agent Bench | 7.77% | #68 of 79 | Official leaderboard | |
| MedCode | 31.9% | #85 of 96 | Official leaderboard | |
| Legal Research Bench | 9.13% | #80 of 88 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Video-MME | 87.7% | #9 of 42 | Model card | |
| Claw-Eval-MM | 51.5% | #3 of 11 | Official leaderboard | |
| MMMU-Pro | 77.9% | #23 of 72 | Model card | |
| OmniDocBench | 87.2% | #1 of 3 | Model card | |
| CharXiv | 81% | #28 of 67 | Model card | |
| Vision Arena | 1,234 | #59 of 136 | Official leaderboard | |
| Daily-Omni | 83.5% | #3 of 6 | Model card | |
| HR-Bench | 88.5% | #1 of 2 | Model card | |
| Video-Holmes | 64% | #5 of 6 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SAGE (Vals) | 43.3% | #50 of 81 | Official leaderboard | |
| Vals Multimodal Index | 52.8% | #23 of 33 | Official leaderboard |
The benchmarks the lab chose to headline, with the scores it gave.