Model comparison
Grok-3 mini vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 41.2 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Grok-3 mini scores higher in 3 categories and MiMo-V2.5-Pro in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.5-Pro leads 26.8 to 13.6.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | xAI | Xiaomi |
| Noometry Index | 41.2 | 45.2 |
| Released | 2025-04-09 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.43 |
| Output $ / M tokens | — | $0.87 |
| Results tracked | 35 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Grok-3 mini: 40.8 (#131), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Grok-3 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Coding | 1379 | 1503 |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1479 |
| SciCode | — | 50.2% |
| WeirdML | 42.6% | — |
| ALE-Bench | — | 899.8 |
Reasoning MiMo-V2.5-Pro leads
Grok-3 mini: 13.6 (#334), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Grok-3 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1488 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 34.4% |
| ARC-AGI-1 | 16.5% | — |
| CritPt | — | 4% |
| DTBench | — | 84.5% |
| LMCA | — | 29.5% |
| Epoch Capabilities Index | 140.35 | — |
Math Grok-3 mini leads
Grok-3 mini: 42.1 (#85), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Grok-3 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1386 | 1481 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| ProofBench | — | 22% |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.4 (#81), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Grok-3 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1395 | 1503 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
Multilingual MiMo-V2.5-Pro leads
Grok-3 mini: 48.1 (#145), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Grok-3 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1352 | 1449 |
| LMArena Chinese | 1387 | 1507 |
| LMArena French | 1357 | 1488 |
| LMArena German | 1349 | 1458 |
| LMArena Japanese | 1342 | 1412 |
| LMArena Korean | 1335 | 1437 |
| LMArena Russian | 1353 | 1450 |
| LMArena Spanish | 1381 | 1471 |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Grok-3 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1357 | 1477 |
| IFEval | 95.1% | — |
Long Context MiMo-V2.5-Pro leads
Grok-3 mini: 41.0 (#147), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Grok-3 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1372 | 1483 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference MiMo-V2.5-Pro leads
Grok-3 mini: 52.5 (#169), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Grok-3 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1370 | 1465 |
| LMArena Creative Writing | 1342 | 1440 |
| LMArena Multi-Turn | 1355 | 1477 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | — | 1493 |
| WildBench | 65.1% | — |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Grok-3 mini better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 41.2 on the Noometry Index.
Is Grok-3 mini or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 40.8 in the Noometry coding category.
How many benchmarks do Grok-3 mini and MiMo-V2.5-Pro share?
17 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and MiMo-V2.5-Pro has 27.