Model comparison
Devstral Small 2505 vs MiMo-V2.5
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 34.3 on the Noometry Index.
Last verified . 2 shared benchmarks.
Mistral AISummary
- They share 2 benchmarks with published results for both. Devstral Small 2505 scores higher in 0 categories and MiMo-V2.5 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.5 leads 28.6 to 19.7.
- The biggest single-benchmark swing is SciCode: 28.8% for Devstral Small 2505 and 43.1% for MiMo-V2.5.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2.5.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 128K.
Side by side
| Devstral Small 2505 | MiMo-V2.5 | |
|---|---|---|
| Provider | Mistral AI | Xiaomi |
| Noometry Index | 34.3 | 43.4 |
| Released | 2025-05-07 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 128K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.10 | $0.14 |
| Output $ / M tokens | $0.30 | $0.28 |
| Results tracked | 4 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
Devstral Small 2505: 38.9 (#166), MiMo-V2.5: 43.9 (#81)
| Benchmark | Devstral Small 2505 | MiMo-V2.5 |
|---|---|---|
| SciCode | 28.8% | 43.1% |
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1438 |
| LMArena Coding | — | 1469 |
| ALE-Bench | — | 513.95 |
Reasoning MiMo-V2.5 leads
Devstral Small 2505: 19.7 (#252), MiMo-V2.5: 28.6 (#101)
| Benchmark | Devstral Small 2505 | MiMo-V2.5 |
|---|---|---|
| CritPt | 0% | 3.7% |
| Kagi LLM Benchmark | 37.7% | — |
| LMArena Hard Prompts | — | 1450 |
Math Not comparable
Devstral Small 2505: —, MiMo-V2.5: 36.8 (#163)
| Benchmark | Devstral Small 2505 | MiMo-V2.5 |
|---|---|---|
| ProofBench | — | 16% |
| LMArena Math | — | 1436 |
Knowledge Not comparable
Devstral Small 2505: —, MiMo-V2.5: 40.8 (#115)
| Benchmark | Devstral Small 2505 | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | — | 1460 |
Multimodal Not comparable
Devstral Small 2505: —, MiMo-V2.5: 39.8 (#54)
| Benchmark | Devstral Small 2505 | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual Not comparable
Devstral Small 2505: —, MiMo-V2.5: 51.9 (#99)
| Benchmark | Devstral Small 2505 | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | — | 1404 |
| LMArena Chinese | — | 1468 |
| LMArena French | — | 1447 |
| LMArena German | — | 1421 |
| LMArena Japanese | — | 1306 |
| LMArena Korean | — | 1363 |
| LMArena Russian | — | 1395 |
| LMArena Spanish | — | 1416 |
Instruction Following Not comparable
Devstral Small 2505: —, MiMo-V2.5: 75.5 (#60)
| Benchmark | Devstral Small 2505 | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | — | 1434 |
Long Context Not comparable
Devstral Small 2505: —, MiMo-V2.5: 44.2 (#73)
| Benchmark | Devstral Small 2505 | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | — | 1445 |
Writing & Preference Not comparable
Devstral Small 2505: —, MiMo-V2.5: 61.6 (#86)
| Benchmark | Devstral Small 2505 | MiMo-V2.5 |
|---|---|---|
| LMArena Text | — | 1428 |
| LMArena Creative Writing | — | 1393 |
| LMArena Multi-Turn | — | 1445 |
Frequently asked questions
Is Devstral Small 2505 better than MiMo-V2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 34.3 on the Noometry Index.
Which is cheaper, Devstral Small 2505 or MiMo-V2.5?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; MiMo-V2.5 lists at $0.14 and $0.28.
Is Devstral Small 2505 or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 128K.
How many benchmarks do Devstral Small 2505 and MiMo-V2.5 share?
2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and MiMo-V2.5 has 23.