Model comparison
MiMo-V2.6-Pro vs Mistral Large
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 31.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
Mistral AISummary
- They share 15 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 9 categories and Mistral Large in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Pro leads 54.5 to 18.2.
- The biggest single-benchmark swing is CritPt: 26.6% for MiMo-V2.6-Pro and 0% for Mistral Large.
- MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $2 / $6 for Mistral Large.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 131K.
Side by side
| MiMo-V2.6-Pro | Mistral Large | |
|---|---|---|
| Provider | Xiaomi | Mistral AI |
| Noometry Index | 50.3 | 31.9 |
| Released | 2026-09-21 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 1.05M | 131K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.43 | $2 |
| Output $ / M tokens | $0.87 | $6 |
| Results tracked | 19 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 55.5 (#23), Mistral Large: 34.3 (#240)
| Benchmark | MiMo-V2.6-Pro | Mistral Large |
|---|---|---|
| SciCode | 60.9% | 36.2% |
| LMArena Coding | 1534 | 1277 |
| ALE-Bench | 1,158 | 264.7 |
| LMArena WebDev | 1629 | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 37.5 (#35), Mistral Large: 28.6 (#89)
| Benchmark | MiMo-V2.6-Pro | Mistral Large |
|---|---|---|
| APEX-Agents | 59.5% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.1 (#50), Mistral Large: 15.8 (#310)
| Benchmark | MiMo-V2.6-Pro | Mistral Large |
|---|---|---|
| CritPt | 26.6% | 0% |
| LMArena Hard Prompts | 1512 | 1257 |
| SimpleBench | — | 22.5% |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Epoch Capabilities Index | — | 128.52 |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 54.5 (#45), Mistral Large: 18.2 (#291)
| Benchmark | MiMo-V2.6-Pro | Mistral Large |
|---|---|---|
| LMArena Math | 1494 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| ProofBench | 70% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.5 (#92), Mistral Large: 30.1 (#230)
| Benchmark | MiMo-V2.6-Pro | Mistral Large |
|---|---|---|
| LMArena Expert | 1543 | 1232 |
| GPQA Diamond | — | 51.3% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multimodal Not comparable
MiMo-V2.6-Pro: 40.8 (#43), Mistral Large: —
| Benchmark | MiMo-V2.6-Pro | Mistral Large |
|---|---|---|
| LMArena Vision | 1264 | — |
Multilingual MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 56.9 (#14), Mistral Large: 40.0 (#219)
| Benchmark | MiMo-V2.6-Pro | Mistral Large |
|---|---|---|
| LMArena Non-English | 1474 | 1237 |
| LMArena Chinese | 1529 | 1240 |
| LMArena Russian | 1480 | 1257 |
| LMArena French | — | 1325 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1188 |
| LMArena Korean | — | 1202 |
| LMArena Spanish | — | 1268 |
Instruction Following MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 78.2 (#12), Mistral Large: 67.9 (#191)
| Benchmark | MiMo-V2.6-Pro | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1493 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 46.0 (#27), Mistral Large: 38.3 (#199)
| Benchmark | MiMo-V2.6-Pro | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1501 | 1261 |
Writing & Preference MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 66.8 (#33), Mistral Large: 40.7 (#242)
| Benchmark | MiMo-V2.6-Pro | Mistral Large |
|---|---|---|
| LMArena Text | 1492 | 1266 |
| LMArena Creative Writing | 1468 | 1243 |
| LMArena Multi-Turn | 1464 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is MiMo-V2.6-Pro better than Mistral Large?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 31.9 on the Noometry Index.
Which is cheaper, MiMo-V2.6-Pro or Mistral Large?
MiMo-V2.6-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Mistral Large lists at $2 and $6.
Is MiMo-V2.6-Pro or Mistral Large better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 131K.
How many benchmarks do MiMo-V2.6-Pro and Mistral Large share?
15 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Mistral Large has 51.