Model comparison
Grok 3 vs MiMo-V2.5
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 39.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Grok 3 scores higher in 3 categories and MiMo-V2.5 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.5 leads 27.8 to 13.8.
- MiMo-V2.5 has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | MiMo-V2.5 | |
|---|---|---|
| Provider | xAI | Xiaomi |
| Noometry Index | 39.6 | 43.0 |
| Released | 2025-04-09 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.28 |
| Results tracked | 40 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
Grok 3: 41.5 (#113), MiMo-V2.5: 43.6 (#75)
| Benchmark | Grok 3 | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1432 | 1469 |
| Aider Polyglot | 53.3% | — |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| WeirdML | 37.2% | — |
| ALE-Bench | — | 513.95 |
Agentic & Tool Use Not comparable
Grok 3: 30.2 (#69), MiMo-V2.5: —
| Benchmark | Grok 3 | MiMo-V2.5 |
|---|---|---|
| BALROG | 29.5% | — |
Reasoning MiMo-V2.5 leads
Grok 3: 13.8 (#322), MiMo-V2.5: 27.8 (#98)
| Benchmark | Grok 3 | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1450 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 3.7% |
| Epoch Capabilities Index | 138.34 | — |
Math Too close to call
Grok 3: 36.2 (#122), MiMo-V2.5: 35.4 (#145)
| Benchmark | Grok 3 | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1390 | 1436 |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| ProofBench | — | 16% |
| Omni-MATH | 46.4% | — |
| MATH Level 5 | 88.7% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.0 (#76), MiMo-V2.5: 40.2 (#109)
| Benchmark | Grok 3 | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1420 | 1459 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |
Multimodal Not comparable
Grok 3: —, MiMo-V2.5: 39.0 (#53)
| Benchmark | Grok 3 | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual Too close to call
Grok 3: 52.5 (#81), MiMo-V2.5: 52.0 (#96)
| Benchmark | Grok 3 | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1411 | 1404 |
| LMArena Chinese | 1448 | 1467 |
| LMArena French | 1460 | 1447 |
| LMArena German | 1431 | 1421 |
| LMArena Japanese | 1389 | 1304 |
| LMArena Korean | 1374 | 1363 |
| LMArena Russian | 1416 | 1395 |
| LMArena Spanish | 1417 | 1412 |
Instruction Following Too close to call
Grok 3: 75.2 (#69), MiMo-V2.5: 75.7 (#55)
| Benchmark | Grok 3 | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1409 | 1433 |
| IFEval | 88.4% | — |
Long Context MiMo-V2.5 leads
Grok 3: 38.7 (#187), MiMo-V2.5: 44.1 (#69)
| Benchmark | Grok 3 | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1439 | 1444 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference MiMo-V2.5 leads
Grok 3: 56.0 (#136), MiMo-V2.5: 61.8 (#82)
| Benchmark | Grok 3 | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1426 | 1427 |
| LMArena Creative Writing | 1414 | 1392 |
| LMArena Multi-Turn | 1424 | 1445 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than MiMo-V2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 39.6 on the Noometry Index.
Is Grok 3 or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 41.5 in the Noometry coding category.
How many benchmarks do Grok 3 and MiMo-V2.5 share?
17 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and MiMo-V2.5 has 23.