Model comparison
Devstral Small 2505 vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.3 to 34.3 on the Noometry Index. Devstral Small 2505 costs 20× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Mistral AISummary
- They share 3 benchmarks with published results for both. Devstral Small 2505 scores higher in 1 category and Mistral Medium in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Devstral Small 2505 leads 38.9 to 34.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.7% for Devstral Small 2505 and 50% for Mistral Medium.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 128K.
Side by side
| Devstral Small 2505 | Mistral Medium | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 34.3 | 36.3 |
| Released | 2025-05-07 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $0.10 | $1.50 |
| Output $ / M tokens | $0.30 | $7.50 |
| Results tracked | 4 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Devstral Small 2505 leads
Devstral Small 2505: 38.9 (#166), Mistral Medium: 34.2 (#243)
| Benchmark | Devstral Small 2505 | Mistral Medium |
|---|---|---|
| SciCode | 28.8% | 40.2% |
| FrontierCode | — | 8% |
| SWE-bench Verified (bash only) | 56.4% | — |
| WeirdML | — | 43.7% |
| LMArena Coding | — | 1434 |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, Mistral Medium: 28.3 (#90)
| Benchmark | Devstral Small 2505 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Mistral Medium leads
Devstral Small 2505: 19.7 (#252), Mistral Medium: 24.0 (#167)
| Benchmark | Devstral Small 2505 | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | 50% |
| CritPt | 0% | 0% |
| LMArena Hard Prompts | — | 1426 |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math Not comparable
Devstral Small 2505: —, Mistral Medium: 28.1 (#245)
| Benchmark | Devstral Small 2505 | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| LMArena Math | — | 1408 |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Not comparable
Devstral Small 2505: —, Mistral Medium: 25.0 (#265)
| Benchmark | Devstral Small 2505 | Mistral Medium |
|---|---|---|
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| LMArena Expert | — | 1408 |
Multimodal Not comparable
Devstral Small 2505: —, Mistral Medium: 35.3 (#88)
| Benchmark | Devstral Small 2505 | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Not comparable
Devstral Small 2505: —, Mistral Medium: 52.1 (#91)
| Benchmark | Devstral Small 2505 | Mistral Medium |
|---|---|---|
| LMArena Non-English | — | 1408 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1459 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1433 |
Instruction Following Not comparable
Devstral Small 2505: —, Mistral Medium: 73.7 (#116)
| Benchmark | Devstral Small 2505 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | — | 1398 |
Long Context Not comparable
Devstral Small 2505: —, Mistral Medium: 42.9 (#114)
| Benchmark | Devstral Small 2505 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1406 |
Writing & Preference Not comparable
Devstral Small 2505: —, Mistral Medium: 60.0 (#103)
| Benchmark | Devstral Small 2505 | Mistral Medium |
|---|---|---|
| LMArena Text | — | 1424 |
| LMArena Creative Writing | — | 1391 |
| Short-Story Creative Writing | — | 77.3% |
| LMArena Multi-Turn | — | 1418 |
Frequently asked questions
Is Devstral Small 2505 better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.3 to 34.3 on the Noometry Index. Devstral Small 2505 costs 20× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or Mistral Medium?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Devstral Small 2505 or Mistral Medium better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 128K.
How many benchmarks do Devstral Small 2505 and Mistral Medium share?
3 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Mistral Medium has 36.