MiMo-V2.5-Pro
Xiaomi / Xiaomi
28scores
20benchmarks
$1 / $3 per 1M tokenscost in/out
Metadata
Xiaomi Closed/API
Aliases: mimo-v2.5-pro, mimo-v2.5-pro-20260422, xiaomi-mimo-v2.5-pro, xiaomi-mimo-v2.5-pro-20260422, xiaomi/mimo-v2.5-pro, xiaomi/mimo-v2.5-pro-20260422
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| Gert Labs Rankings | Agentic | 4 | 0.66 | 2026-05-11 |
| ITBench-AA | Agentic | 8 | 38.2% | 2026-05-28 |
| Tau2-Bench Telecom | Agentic | 28 | 94.2% | 2026-05-11 |
| Tau2-Bench Telecom | Agentic | 129 | 72.5% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 29 | 43.2% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 59 | 35.6% | 2026-05-11 |
| ALE-Bench | Coding | 34 | 899.80 | 2026-05-06 |
| Arena AI Code | Coding | 11 | 1475 | 2026-05-06 |
| BLXBench | Coding | 15 | 44 | 2026-05-06 |
| DeepSWE | Coding | 9 | 19.47 | 2026-05-26 |
| LMArena WebDev Arena | Coding | 11 | 1476.42 | 2026-05-06 |
| SciCode | Coding | 17 | 50.2% | 2026-05-11 |
| SciCode | Coding | 120 | 39.1% | 2026-05-11 |
| AA-Omniscience | Factuality | 11 | 3.6 | 2026-05-11 |
| LMArena Text Arena | Generalization | 16 | 1457.88 | 2026-05-06 |
| PhysicianBench | Healthcare | 8 | 16.7 +/- 4.0 | 2026-05-27 |
| AIIQ Composite IQ | Intelligence | 25 | 108 | 2026-05-12 |
| Artificial Analysis Intelligence Index | Intelligence | 8 | 53.83 | 2026-05-11 |
| Artificial Analysis Intelligence Index | Intelligence | 106 | 35.59 | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 16 | 33.8% | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 107 | 13.3% | 2026-05-11 |
| Artificial Analysis Openness Index | Openness | 128 | 38.89 | 2026-05-11 |
| Context Arena | Reasoning | 36 | 36.22 | 2026-05-06 |
| Context Arena | Reasoning | 58 | 24.25 | 2026-05-06 |
| GPQA Diamond | Reasoning | 40 | 86.6% | 2026-05-11 |
| GPQA Diamond | Reasoning | 147 | 76.2% | 2026-05-11 |
| CritPt | Science | 40 | 4% | 2026-05-11 |
| CritPt | Science | 86 | 1.1% | 2026-05-11 |
No matching rows.