Model comparison
Codestral vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 30.6 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and MiMo-V2.5-Pro in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.5-Pro leads 47.4 to 27.3.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 256K.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| Codestral | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Mistral AI | Xiaomi |
| Noometry Index | 30.6 | 45.2 |
| Released | 2024-05-29 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 256K | 1.05M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.30 | $0.43 |
| Output $ / M tokens | $0.90 | $0.87 |
| Results tracked | 7 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Codestral: 27.3 (#321), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Codestral | MiMo-V2.5-Pro |
|---|---|---|
| ALE-Bench | 137.78 | 899.8 |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1479 |
| SciCode | — | 50.2% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1503 |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning MiMo-V2.5-Pro leads
Codestral: 19.8 (#251), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Codestral | MiMo-V2.5-Pro |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 34.4% |
| CritPt | — | 4% |
| LMArena Hard Prompts | — | 1488 |
| DTBench | — | 84.5% |
| LMCA | — | 29.5% |
Math Not comparable
Codestral: —, MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Codestral | MiMo-V2.5-Pro |
|---|---|---|
| ProofBench | — | 22% |
| LMArena Math | — | 1481 |
Knowledge Not comparable
Codestral: —, MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Codestral | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | — | 1503 |
Multilingual Not comparable
Codestral: —, MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Codestral | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | — | 1449 |
| LMArena Chinese | — | 1507 |
| LMArena French | — | 1488 |
| LMArena German | — | 1458 |
| LMArena Japanese | — | 1412 |
| LMArena Korean | — | 1437 |
| LMArena Russian | — | 1450 |
| LMArena Spanish | — | 1471 |
Instruction Following Not comparable
Codestral: —, MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Codestral | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | — | 1477 |
Long Context Not comparable
Codestral: —, MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Codestral | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | — | 1483 |
Writing & Preference Not comparable
Codestral: —, MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Codestral | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | — | 1465 |
| LMArena Creative Writing | — | 1440 |
| EQ-Bench Creative Writing | — | 1493 |
| EQ-Bench 4 | — | 1208 |
| LMArena Multi-Turn | — | 1477 |
Frequently asked questions
Is Codestral better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 30.6 on the Noometry Index.
Which is cheaper, Codestral or MiMo-V2.5-Pro?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is Codestral or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 256K.
How many benchmarks do Codestral and MiMo-V2.5-Pro share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and MiMo-V2.5-Pro has 27.