# Devstral Small 2505 vs GPT-4 Turbo

> Devstral Small 2505 is the stronger model overall, scoring 33.9 to 30.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/devstral-small-vs-gpt-4-turbo
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Devstral Small 2505 leads 38.6 to 33.4.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Devstral Small 2505 has downloadable open weights; the other is API-only.

## Snapshot

| | Devstral Small 2505 | GPT-4 Turbo |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 33.9 | 30.3 |
| Rank | 228 | 281 |
| Context | 128K | 128K |
| Input $/M | $0.10 | $10 |
| Output $/M | $0.30 | $30 |
| Weights | Open | Proprietary |

## Coding

- Devstral Small 2505: 38.6 (#160)
- GPT-4 Turbo: 33.4 (#247)

| Benchmark | Devstral Small 2505 | GPT-4 Turbo |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| WeirdML | — | 18% |
| BigCodeBench Instruct | — | 48.2% |
| LMArena Coding | — | 1268 |
| BigCodeBench Complete | — | 58.2% |
| HumanEval+ | — | 86.6% |
| MBPP+ | — | 73.3% |

## Agentic & Tool Use

- Devstral Small 2505: —
- GPT-4 Turbo: —

| Benchmark | Devstral Small 2505 | GPT-4 Turbo |
|---|---|---|
| METR Time Horizons | — | 36.7% |

## Reasoning

- Devstral Small 2505: 19.1 (#243)
- GPT-4 Turbo: 14.9 (#311)

| Benchmark | Devstral Small 2505 | GPT-4 Turbo |
|---|---|---|
| SimpleBench | — | 25.1% |
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 6% |
| LMArena Hard Prompts | — | 1251 |
| DTBench | — | 61.6% |
| LMCA | — | 9.8% |
| Epoch Capabilities Index | — | 127.25 |
| ForecastBench | — | 59.4 |

## Math

- Devstral Small 2505: —
- GPT-4 Turbo: 8.6 (#316)

| Benchmark | Devstral Small 2505 | GPT-4 Turbo |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 0.7% |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| LMArena Math | — | 1272 |
| MATH Level 5 | — | 46.7% |

## Knowledge

- Devstral Small 2505: —
- GPT-4 Turbo: 24.3 (#263)

| Benchmark | Devstral Small 2505 | GPT-4 Turbo |
|---|---|---|
| GPQA Diamond | — | 46.6% |
| Confabulations | — | 28.4% |
| LMArena Expert | — | 1223 |
| MMLU | — | 81.3% |

## Multimodal

- Devstral Small 2505: —
- GPT-4 Turbo: 30.0 (#104)

| Benchmark | Devstral Small 2505 | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | — | 1090 |

## Multilingual

- Devstral Small 2505: —
- GPT-4 Turbo: 40.7 (#211)

| Benchmark | Devstral Small 2505 | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | — | 1245 |
| LMArena Chinese | — | 1242 |
| LMArena French | — | 1275 |
| LMArena German | — | 1259 |
| LMArena Japanese | — | 1194 |
| LMArena Korean | — | 1187 |
| LMArena Russian | — | 1259 |
| LMArena Spanish | — | 1260 |

## Instruction Following

- Devstral Small 2505: —
- GPT-4 Turbo: 66.0 (#211)

| Benchmark | Devstral Small 2505 | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | — | 1250 |

## Long Context

- Devstral Small 2505: —
- GPT-4 Turbo: 38.0 (#200)

| Benchmark | Devstral Small 2505 | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | — | 1254 |

## Writing & Preference

- Devstral Small 2505: —
- GPT-4 Turbo: 47.9 (#201)

| Benchmark | Devstral Small 2505 | GPT-4 Turbo |
|---|---|---|
| LMArena Text | — | 1272 |
| LMArena Creative Writing | — | 1269 |
| LMArena Multi-Turn | — | 1267 |

## FAQ

### Is Devstral Small 2505 better than GPT-4 Turbo?

Devstral Small 2505 is the stronger model overall, scoring 33.9 to 30.3 on the Noometry Index.

### Which is cheaper, Devstral Small 2505 or GPT-4 Turbo?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; GPT-4 Turbo lists at $10 and $30.

### Is Devstral Small 2505 or GPT-4 Turbo better for coding?

Devstral Small 2505 scores higher on coding benchmarks: 38.6 versus 33.4 in the Noometry coding category.

### Which has the bigger context window?

Both accept 128K tokens.

### How many benchmarks do Devstral Small 2505 and GPT-4 Turbo share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and GPT-4 Turbo has 36.