Model comparison
MiMo-V2.5 vs Mistral Medium
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 36.3 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. MiMo-V2.5 scores higher in 8 categories and Mistral Medium in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiMo-V2.5 leads 40.8 to 25.0.
- The biggest single-benchmark swing is ProofBench: 16% for MiMo-V2.5 and 9% for Mistral Medium.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 262K.
Side by side
| MiMo-V2.5 | Mistral Medium | |
|---|---|---|
| Provider | Xiaomi | Mistral AI |
| Noometry Index | 43.4 | 36.3 |
| Released | 2026-04-22 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $0.14 | $1.50 |
| Output $ / M tokens | $0.28 | $7.50 |
| Results tracked | 23 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
MiMo-V2.5: 43.9 (#81), Mistral Medium: 34.2 (#243)
| Benchmark | MiMo-V2.5 | Mistral Medium |
|---|---|---|
| SciCode | 43.1% | 40.2% |
| LMArena Coding | 1469 | 1434 |
| ALE-Bench | 513.95 | 763.98 |
| FrontierCode | — | 8% |
| LMArena WebDev | 1438 | — |
| WeirdML | — | 43.7% |
Agentic & Tool Use Not comparable
MiMo-V2.5: —, Mistral Medium: 28.3 (#90)
| Benchmark | MiMo-V2.5 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 28.6 (#101), Mistral Medium: 24.0 (#167)
| Benchmark | MiMo-V2.5 | Mistral Medium |
|---|---|---|
| CritPt | 3.7% | 0% |
| LMArena Hard Prompts | 1450 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math MiMo-V2.5 leads
MiMo-V2.5: 36.8 (#163), Mistral Medium: 28.1 (#245)
| Benchmark | MiMo-V2.5 | Mistral Medium |
|---|---|---|
| ProofBench | 16% | 9% |
| LMArena Math | 1436 | 1408 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge MiMo-V2.5 leads
MiMo-V2.5: 40.8 (#115), Mistral Medium: 25.0 (#265)
| Benchmark | MiMo-V2.5 | Mistral Medium |
|---|---|---|
| LMArena Expert | 1460 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal MiMo-V2.5 leads
MiMo-V2.5: 39.8 (#54), Mistral Medium: 35.3 (#88)
| Benchmark | MiMo-V2.5 | Mistral Medium |
|---|---|---|
| LMArena Vision | 1247 | 1172 |
Multilingual Too close to call
MiMo-V2.5: 51.9 (#99), Mistral Medium: 52.1 (#91)
| Benchmark | MiMo-V2.5 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1404 | 1408 |
| LMArena Chinese | 1468 | 1447 |
| LMArena French | 1447 | 1459 |
| LMArena German | 1421 | 1432 |
| LMArena Japanese | 1306 | 1378 |
| LMArena Korean | 1363 | 1380 |
| LMArena Russian | 1395 | 1411 |
| LMArena Spanish | 1416 | 1433 |
Instruction Following MiMo-V2.5 leads
MiMo-V2.5: 75.5 (#60), Mistral Medium: 73.7 (#116)
| Benchmark | MiMo-V2.5 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1434 | 1398 |
Long Context MiMo-V2.5 leads
MiMo-V2.5: 44.2 (#73), Mistral Medium: 42.9 (#114)
| Benchmark | MiMo-V2.5 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1445 | 1406 |
Writing & Preference MiMo-V2.5 leads
MiMo-V2.5: 61.6 (#86), Mistral Medium: 60.0 (#103)
| Benchmark | MiMo-V2.5 | Mistral Medium |
|---|---|---|
| LMArena Text | 1428 | 1424 |
| LMArena Creative Writing | 1393 | 1391 |
| LMArena Multi-Turn | 1445 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
Frequently asked questions
Is MiMo-V2.5 better than Mistral Medium?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 36.3 on the Noometry Index.
Which is cheaper, MiMo-V2.5 or Mistral Medium?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is MiMo-V2.5 or Mistral Medium better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 262K.
How many benchmarks do MiMo-V2.5 and Mistral Medium share?
22 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Mistral Medium has 36.