Model comparison
Devstral Small 2505 vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 34.3 on the Noometry Index. Devstral Small 2505 costs 233× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Devstral Small 2505 scores higher in 0 categories and o3-pro in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where o3-pro leads 55.5 to 38.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.7% for Devstral Small 2505 and 72.1% for o3-pro.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $20 / $80 for o3-pro.
- o3-pro accepts more context: 200K tokens versus 128K.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | o3-pro | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 34.3 | 42.9 |
| Released | 2025-05-07 | 2025-06-10 |
| Weights | Open | Proprietary |
| Context window | 128K | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $0.10 | $20 |
| Output $ / M tokens | $0.30 | $80 |
| Results tracked | 4 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Devstral Small 2505: 38.9 (#166), o3-pro: 55.5 (#24)
| Benchmark | Devstral Small 2505 | o3-pro |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| Aider Polyglot | — | 84.9% |
| SciCode | 28.8% | — |
| WeirdML | — | 58.2% |
Reasoning o3-pro leads
Devstral Small 2505: 19.7 (#252), o3-pro: 23.8 (#171)
| Benchmark | Devstral Small 2505 | o3-pro |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | 72.1% |
| ARC-AGI-2 | — | 4.9% |
| ARC-AGI-1 | — | 59.3% |
| CritPt | 0% | — |
| DTBench | — | 86.9% |
| LMCA | — | 38.5% |
| Epoch Capabilities Index | — | 147.42 |
Knowledge Not comparable
Devstral Small 2505: —, o3-pro: 29.5 (#238)
| Benchmark | Devstral Small 2505 | o3-pro |
|---|---|---|
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
Long Context Not comparable
Devstral Small 2505: —, o3-pro: 72.2 (#1)
| Benchmark | Devstral Small 2505 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
Writing & Preference Not comparable
Devstral Small 2505: —, o3-pro: 57.1 (#133)
| Benchmark | Devstral Small 2505 | o3-pro |
|---|---|---|
| Short-Story Creative Writing | — | 84.4% |
Frequently asked questions
Is Devstral Small 2505 better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 34.3 on the Noometry Index. Devstral Small 2505 costs 233× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or o3-pro?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; o3-pro lists at $20 and $80.
Is Devstral Small 2505 or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
o3-pro does, with 200K tokens against 128K.
How many benchmarks do Devstral Small 2505 and o3-pro share?
1 benchmark has published results for both models. Devstral Small 2505 has 4 scored results on Noometry and o3-pro has 12.