# Devstral Small 2505 vs o3-pro

> o3-pro is the stronger model overall, scoring 42.7 to 33.9 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.

- Canonical page: https://noometry.com/compare/devstral-small-vs-o3-pro
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- 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 55.1 to 38.6.
- 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.

## Snapshot

| | Devstral Small 2505 | o3-pro |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 33.9 | 42.7 |
| Rank | 228 | 94 |
| Context | 128K | 200K |
| Input $/M | $0.10 | $20 |
| Output $/M | $0.30 | $80 |
| Weights | Open | Proprietary |

## Coding

- Devstral Small 2505: 38.6 (#160)
- o3-pro: 55.1 (#22)

| Benchmark | Devstral Small 2505 | o3-pro |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| Aider Polyglot | — | 84.9% |
| SciCode | 28.8% | — |
| WeirdML | — | 58.2% |

## Reasoning

- Devstral Small 2505: 19.1 (#243)
- o3-pro: 24.1 (#152)

| 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 | — | 147.43 |

## Knowledge

- Devstral Small 2505: —
- o3-pro: 29.0 (#234)

| Benchmark | Devstral Small 2505 | o3-pro |
|---|---|---|
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |

## Long Context

- Devstral Small 2505: —
- o3-pro: 72.1 (#1)

| Benchmark | Devstral Small 2505 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |

## Writing & Preference

- Devstral Small 2505: —
- o3-pro: 57.1 (#128)

| Benchmark | Devstral Small 2505 | o3-pro |
|---|---|---|
| Short-Story Creative Writing | — | 84.4% |

## FAQ

### Is Devstral Small 2505 better than o3-pro?

o3-pro is the stronger model overall, scoring 42.7 to 33.9 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: 55.1 versus 38.6 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.