# Devstral 2 vs GPT-6 Sol

> GPT-6 Sol has enough public results to be ranked (#46); Devstral 2 does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/devstral-2-vs-gpt-6-sol
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Devstral 2 scores higher in 0 categories and GPT-6 Sol in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where GPT-6 Sol leads 59.6 to 33.0.
- Devstral 2 is cheaper at $0.40 / $2 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 262K.
- Devstral 2 has downloadable open weights; the other is API-only.

## Snapshot

| | Devstral 2 | GPT-6 Sol |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 35.8 | 49.2 |
| Rank | — | 46 |
| Context | 262K | 1.05M |
| Input $/M | $0.40 | $2 |
| Output $/M | $2 | $10 |
| Weights | Open | Proprietary |

## Coding

- Devstral 2: 33.0 (#253)
- GPT-6 Sol: 59.6 (#11)

| Benchmark | Devstral 2 | GPT-6 Sol |
|---|---|---|
| LMArena WebDev | 1196 | 1692 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| SWE-bench Verified (bash only) | 53.8% | — |
| LMArena Coding | — | 1453 |

## Agentic & Tool Use

- Devstral 2: —
- GPT-6 Sol: 33.5 (#49)

| Benchmark | Devstral 2 | GPT-6 Sol |
|---|---|---|
| GDP.pdf | — | 28% |

## Reasoning

- Devstral 2: —
- GPT-6 Sol: 49.3 (#34)

| Benchmark | Devstral 2 | GPT-6 Sol |
|---|---|---|
| NYT Connections (extended) | — | 90.1% |
| EBR-Bench | — | 53.3% |
| LMArena Hard Prompts | — | 1420 |

## Math

- Devstral 2: —
- GPT-6 Sol: 35.8 (#135)

| Benchmark | Devstral 2 | GPT-6 Sol |
|---|---|---|
| LMArena Math | — | 1404 |

## Knowledge

- Devstral 2: —
- GPT-6 Sol: 43.0 (#87)

| Benchmark | Devstral 2 | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | — | 6.5% |
| LMArena Expert | — | 1449 |

## Multimodal

- Devstral 2: —
- GPT-6 Sol: 47.6 (#9)

| Benchmark | Devstral 2 | GPT-6 Sol |
|---|---|---|
| Furniture Assembly | — | 58.3% |

## Multilingual

- Devstral 2: —
- GPT-6 Sol: 51.0 (#113)

| Benchmark | Devstral 2 | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | — | 1389 |
| LMArena Chinese | — | 1416 |
| LMArena Russian | — | 1407 |
| LMArena Spanish | — | 1377 |

## Instruction Following

- Devstral 2: —
- GPT-6 Sol: 74.4 (#97)

| Benchmark | Devstral 2 | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | — | 1406 |

## Long Context

- Devstral 2: —
- GPT-6 Sol: 43.2 (#100)

| Benchmark | Devstral 2 | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | — | 1415 |

## Writing & Preference

- Devstral 2: —
- GPT-6 Sol: 72.3 (#15)

| Benchmark | Devstral 2 | GPT-6 Sol |
|---|---|---|
| LMArena Text | — | 1396 |
| LMArena Creative Writing | — | 1392 |
| EQ-Bench Creative Writing | — | 2125 |
| LMArena Multi-Turn | — | 1405 |

## FAQ

### Is Devstral 2 better than GPT-6 Sol?

GPT-6 Sol has enough public results to be ranked (#46); Devstral 2 does not yet, so treat this comparison as directional.

### Which is cheaper, Devstral 2 or GPT-6 Sol?

Devstral 2 is cheaper. It lists at $0.40 per million input tokens and $2 per million output tokens; GPT-6 Sol lists at $2 and $10.

### Is Devstral 2 or GPT-6 Sol better for coding?

GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 33.0 in the Noometry coding category.

### Which has the bigger context window?

GPT-6 Sol does, with 1.05M tokens against 262K.

### How many benchmarks do Devstral 2 and GPT-6 Sol share?

1 benchmark has published results for both models. Devstral 2 has 2 scored results on Noometry and GPT-6 Sol has 22.