Model comparison
Devstral Small 2505 vs GPT-4.1 nano
Devstral Small 2505 is the stronger model overall, scoring 34.3 to 27.9 on the Noometry Index.
Last verified . 3 shared benchmarks.
Mistral AISummary
- They share 3 benchmarks with published results for both. Devstral Small 2505 scores higher in 2 categories and GPT-4.1 nano in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Devstral Small 2505 leads 38.9 to 24.1.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.10 / $0.40 for GPT-4.1 nano.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 128K.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | GPT-4.1 nano | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 34.3 | 27.9 |
| Released | 2025-05-07 | 2025-04-14 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 128K | 33K |
| Input $ / M tokens | $0.10 | $0.10 |
| Output $ / M tokens | $0.30 | $0.40 |
| Results tracked | 4 | 38 |
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), GPT-4.1 nano: 24.1 (#330)
| Benchmark | Devstral Small 2505 | GPT-4.1 nano |
|---|---|---|
| SciCode | 28.8% | 25.9% |
| SWE-bench Verified (bash only) | 56.4% | — |
| Aider Polyglot | — | 8.9% |
| WeirdML | — | 19% |
| LMArena Coding | — | 1306 |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, GPT-4.1 nano: 26.5 (#104)
| Benchmark | Devstral Small 2505 | GPT-4.1 nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 33% |
Reasoning Devstral Small 2505 leads
Devstral Small 2505: 19.7 (#252), GPT-4.1 nano: 8.5 (#349)
| Benchmark | Devstral Small 2505 | GPT-4.1 nano |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | 33.3% |
| CritPt | 0% | 0% |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 0% |
| LMArena Hard Prompts | — | 1286 |
| DTBench | — | 52.5% |
| LMCA | — | 5.5% |
| Epoch Capabilities Index | — | 129.62 |
Math Not comparable
Devstral Small 2505: —, GPT-4.1 nano: 26.9 (#252)
| Benchmark | Devstral Small 2505 | GPT-4.1 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 28.9% |
| Omni-MATH | — | 36.7% |
| LMArena Math | — | 1274 |
| MATH Level 5 | — | 70% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Not comparable
Devstral Small 2505: —, GPT-4.1 nano: 21.8 (#273)
| Benchmark | Devstral Small 2505 | GPT-4.1 nano |
|---|---|---|
| GPQA Diamond | — | 48.9% |
| SimpleQA Verified | — | 6% |
| MMLU-Pro | — | 55% |
| GPQA (HELM) | — | 50.7% |
| LMArena Expert | — | 1272 |
Multimodal Not comparable
Devstral Small 2505: —, GPT-4.1 nano: 29.2 (#113)
| Benchmark | Devstral Small 2505 | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | — | 1063 |
Multilingual Not comparable
Devstral Small 2505: —, GPT-4.1 nano: 41.6 (#205)
| Benchmark | Devstral Small 2505 | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | — | 1260 |
| LMArena Chinese | — | 1270 |
| LMArena German | — | 1288 |
| LMArena Japanese | — | 1198 |
| LMArena Russian | — | 1261 |
Instruction Following Not comparable
Devstral Small 2505: —, GPT-4.1 nano: 67.8 (#193)
| Benchmark | Devstral Small 2505 | GPT-4.1 nano |
|---|---|---|
| IFEval | — | 84.3% |
| LMArena Instruction Following | — | 1267 |
Long Context Not comparable
Devstral Small 2505: —, GPT-4.1 nano: 23.7 (#296)
| Benchmark | Devstral Small 2505 | GPT-4.1 nano |
|---|---|---|
| Fiction.LiveBench | — | 25% |
| LMArena Longer Query | — | 1283 |
Writing & Preference Not comparable
Devstral Small 2505: —, GPT-4.1 nano: 40.5 (#243)
| Benchmark | Devstral Small 2505 | GPT-4.1 nano |
|---|---|---|
| LMArena Text | — | 1285 |
| LMArena Creative Writing | — | 1260 |
| EQ-Bench Creative Writing | — | 946 |
| WildBench | — | 81.2% |
| LMArena Multi-Turn | — | 1277 |
Frequently asked questions
Is Devstral Small 2505 better than GPT-4.1 nano?
Devstral Small 2505 is the stronger model overall, scoring 34.3 to 27.9 on the Noometry Index.
Which is cheaper, Devstral Small 2505 or GPT-4.1 nano?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; GPT-4.1 nano lists at $0.10 and $0.40.
Is Devstral Small 2505 or GPT-4.1 nano better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 128K.
How many benchmarks do Devstral Small 2505 and GPT-4.1 nano share?
3 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and GPT-4.1 nano has 38.