Model comparison
Grok-3 mini vs MiMo-V2.6-Pro
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 41.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Grok-3 mini scores higher in 2 categories and MiMo-V2.6-Pro in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.6-Pro leads 43.1 to 13.6.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | xAI | Xiaomi |
| Noometry Index | 41.2 | 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 | 35 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
Grok-3 mini: 40.8 (#131), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | Grok-3 mini | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Coding | 1379 | 1534 |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1629 |
| SciCode | — | 60.9% |
| WeirdML | 42.6% | — |
| ALE-Bench | — | 1,158 |
Agentic & Tool Use Not comparable
Grok-3 mini: —, MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | Grok-3 mini | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |
Reasoning MiMo-V2.6-Pro leads
Grok-3 mini: 13.6 (#334), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | Grok-3 mini | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1512 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| CritPt | — | 26.6% |
| Epoch Capabilities Index | 140.35 | — |
Math MiMo-V2.6-Pro leads
Grok-3 mini: 42.1 (#85), MiMo-V2.6-Pro: 54.5 (#45)
| Benchmark | Grok-3 mini | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1386 | 1494 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| ProofBench | — | 70% |
| 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-V2.6-Pro: 43.5 (#92)
| Benchmark | Grok-3 mini | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1395 | 1543 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
Multimodal Not comparable
Grok-3 mini: —, MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | Grok-3 mini | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |
Multilingual MiMo-V2.6-Pro leads
Grok-3 mini: 48.1 (#145), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | Grok-3 mini | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1352 | 1474 |
| LMArena Chinese | 1387 | 1529 |
| LMArena Russian | 1353 | 1480 |
| LMArena French | 1357 | — |
| LMArena German | 1349 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1335 | — |
| LMArena Spanish | 1381 | — |
Instruction Following Too close to call
Grok-3 mini: 78.5 (#9), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | Grok-3 mini | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1357 | 1493 |
| IFEval | 95.1% | — |
Long Context MiMo-V2.6-Pro leads
Grok-3 mini: 41.0 (#147), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | Grok-3 mini | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1372 | 1501 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference MiMo-V2.6-Pro leads
Grok-3 mini: 52.5 (#169), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | Grok-3 mini | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1370 | 1492 |
| LMArena Creative Writing | 1342 | 1468 |
| LMArena Multi-Turn | 1355 | 1464 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than MiMo-V2.6-Pro?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 41.2 on the Noometry Index.
Is Grok-3 mini or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 40.8 in the Noometry coding category.
How many benchmarks do Grok-3 mini and MiMo-V2.6-Pro share?
12 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and MiMo-V2.6-Pro has 19.