# Codestral vs GPT-6.1 Sol

> GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 30.6 on the Noometry Index. Codestral costs 8.9× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/codestral-vs-gpt-6-1-sol
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where GPT-6.1 Sol leads 81.9 to 19.8.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 256K.

## Snapshot

| | Codestral | GPT-6.1 Sol |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 30.6 | 65.6 |
| Rank | 290 | 6 |
| Context | 256K | 1.05M |
| Input $/M | $0.30 | $2 |
| Output $/M | $0.90 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Codestral: 27.3 (#321)
- GPT-6.1 Sol: 63.2 (#8)

| Benchmark | Codestral | GPT-6.1 Sol |
|---|---|---|
| DeepSWE | — | 75.2% |
| FrontierCode | — | 50.2% |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1755 |
| SciCode | — | 55.8% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1487 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Agentic & Tool Use

- Codestral: —
- GPT-6.1 Sol: 39.6 (#26)

| Benchmark | Codestral | GPT-6.1 Sol |
|---|---|---|
| APEX-Agents | — | 60% |
| GDP.pdf | — | 32% |

## Reasoning

- Codestral: 19.8 (#251)
- GPT-6.1 Sol: 81.9 (#2)

| Benchmark | Codestral | GPT-6.1 Sol |
|---|---|---|
| ARC-AGI-2 | — | 94.2% |
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 95.5% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 31.7% |
| Chess Puzzles | — | 61% |
| EBR-Bench | — | 54.3% |
| LMArena Hard Prompts | — | 1466 |
| Mystery Game Puzzles | — | 80% |
| Epoch Capabilities Index | — | 166.09 |

## Math

- Codestral: —
- GPT-6.1 Sol: 93.7 (#1)

| Benchmark | Codestral | GPT-6.1 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 93.7% |
| FrontierMath Tier 4 | — | 100% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 99% |
| LMArena Math | — | 1464 |

## Knowledge

- Codestral: —
- GPT-6.1 Sol: 71.8 (#4)

| Benchmark | Codestral | GPT-6.1 Sol |
|---|---|---|
| GPQA Diamond | — | 95.4% |
| SimpleQA Verified | — | 73.9% |
| LMArena Expert | — | 1502 |

## Multimodal

- Codestral: —
- GPT-6.1 Sol: 52.7 (#5)

| Benchmark | Codestral | GPT-6.1 Sol |
|---|---|---|
| LMArena Vision | — | 1288 |
| Furniture Assembly | — | 80% |

## Multilingual

- Codestral: —
- GPT-6.1 Sol: 54.3 (#46)

| Benchmark | Codestral | GPT-6.1 Sol |
|---|---|---|
| LMArena Non-English | — | 1438 |
| LMArena Chinese | — | 1477 |
| LMArena Russian | — | 1455 |

## Instruction Following

- Codestral: —
- GPT-6.1 Sol: 77.0 (#29)

| Benchmark | Codestral | GPT-6.1 Sol |
|---|---|---|
| LMArena Instruction Following | — | 1468 |

## Long Context

- Codestral: —
- GPT-6.1 Sol: 44.9 (#54)

| Benchmark | Codestral | GPT-6.1 Sol |
|---|---|---|
| LMArena Longer Query | — | 1465 |

## Writing & Preference

- Codestral: —
- GPT-6.1 Sol: 63.6 (#63)

| Benchmark | Codestral | GPT-6.1 Sol |
|---|---|---|
| LMArena Text | — | 1447 |
| LMArena Creative Writing | — | 1432 |
| LMArena Multi-Turn | — | 1449 |

## FAQ

### Is Codestral better than GPT-6.1 Sol?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 30.6 on the Noometry Index. Codestral costs 8.9× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.

### Which is cheaper, Codestral or GPT-6.1 Sol?

Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; GPT-6.1 Sol lists at $2 and $10.

### Is Codestral or GPT-6.1 Sol better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 27.3 in the Noometry coding category.

### Which has the bigger context window?

GPT-6.1 Sol does, with 1.05M tokens against 256K.

### How many benchmarks do Codestral and GPT-6.1 Sol share?

0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and GPT-6.1 Sol has 34.