Model comparison
Grok 3 vs MiMo-V2.6-Pro
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 39.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Grok 3 scores higher in 1 category and MiMo-V2.6-Pro in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.6-Pro leads 43.1 to 13.7.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | xAI | Xiaomi |
| Noometry Index | 39.9 | 50.3 |
| Released | 2025-04-09 | 2026-09-21 |
| Weights | Proprietary | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.43 |
| Output $ / M tokens | — | $0.87 |
| Results tracked | 40 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
Grok 3: 41.9 (#115), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | Grok 3 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Coding | 1432 | 1534 |
| Aider Polyglot | 53.3% | — |
| LMArena WebDev | — | 1629 |
| SciCode | — | 60.9% |
| WeirdML | 37.2% | — |
| ALE-Bench | — | 1,158 |
Agentic & Tool Use MiMo-V2.6-Pro leads
Grok 3: 30.5 (#76), MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | Grok 3 | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |
| BALROG | 29.5% | — |
Reasoning MiMo-V2.6-Pro leads
Grok 3: 13.7 (#333), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | Grok 3 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1434 | 1512 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 26.6% |
| Epoch Capabilities Index | 138.33 | — |
Math MiMo-V2.6-Pro leads
Grok 3: 38.0 (#145), MiMo-V2.6-Pro: 54.5 (#45)
| Benchmark | Grok 3 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1391 | 1494 |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| ProofBench | — | 70% |
| 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: 46.2 (#82), MiMo-V2.6-Pro: 43.5 (#92)
| Benchmark | Grok 3 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1421 | 1543 |
| 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-V2.6-Pro: 40.8 (#43)
| Benchmark | Grok 3 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |
Multilingual MiMo-V2.6-Pro leads
Grok 3: 52.3 (#87), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | Grok 3 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1410 | 1474 |
| LMArena Chinese | 1448 | 1529 |
| LMArena Russian | 1416 | 1480 |
| LMArena French | 1460 | — |
| LMArena German | 1431 | — |
| LMArena Japanese | 1387 | — |
| LMArena Korean | 1373 | — |
| LMArena Spanish | 1417 | — |
Instruction Following MiMo-V2.6-Pro leads
Grok 3: 75.0 (#73), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | Grok 3 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1409 | 1493 |
| IFEval | 88.4% | — |
Long Context MiMo-V2.6-Pro leads
Grok 3: 38.7 (#192), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | Grok 3 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1439 | 1501 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference MiMo-V2.6-Pro leads
Grok 3: 55.8 (#141), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | Grok 3 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1426 | 1492 |
| LMArena Creative Writing | 1414 | 1468 |
| LMArena Multi-Turn | 1425 | 1464 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than MiMo-V2.6-Pro?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 39.9 on the Noometry Index.
Is Grok 3 or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 41.9 in the Noometry coding category.
How many benchmarks do Grok 3 and MiMo-V2.6-Pro share?
12 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and MiMo-V2.6-Pro has 19.