# Codestral vs Qwen2.5 7B Instruct

> Codestral is the stronger model overall, scoring 30.1 to 28.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codestral-vs-qwen2-5-7b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Codestral scores higher in 1 category and Qwen2.5 7B Instruct in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen2.5 7B Instruct leads 35.9 to 26.9.
- The biggest single-benchmark swing is BigCodeBench Complete: 52.5% for Codestral and 46.1% for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Codestral accepts more context: 256K tokens versus 131K.

## Snapshot

| | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.1 | 28.6 |
| Rank | 287 | 314 |
| Context | 256K | 131K |
| Input $/M | $0.30 | $0.17 |
| Output $/M | $0.90 | $0.70 |
| Weights | Open | Open |

## Coding

- Codestral: 26.9 (#316)
- Qwen2.5 7B Instruct: 35.9 (#204)

| Benchmark | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | 41.8% | 37.6% |
| BigCodeBench Complete | 52.5% | 46.1% |
| Aider Polyglot | 11.1% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Agentic & Tool Use

- Codestral: —
- Qwen2.5 7B Instruct: 23.5 (#117)

| Benchmark | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |

## Reasoning

- Codestral: 19.1 (#244)
- Qwen2.5 7B Instruct: 14.3 (#317)

| Benchmark | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| Epoch Capabilities Index | — | 118.44 |

## Math

- Codestral: —
- Qwen2.5 7B Instruct: 11.8 (#300)

| Benchmark | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |

## Knowledge

- Codestral: —
- Qwen2.5 7B Instruct: 17.0 (#281)

| Benchmark | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| MMLU | — | 72.9% |

## Instruction Following

- Codestral: —
- Qwen2.5 7B Instruct: 63.4 (#226)

| Benchmark | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |

## Writing & Preference

- Codestral: —
- Qwen2.5 7B Instruct: 48.8 (#194)

| Benchmark | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | — | 73.1% |

## FAQ

### Is Codestral better than Qwen2.5 7B Instruct?

Codestral is the stronger model overall, scoring 30.1 to 28.6 on the Noometry Index.

### Which is cheaper, Codestral or Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Codestral lists at $0.30 and $0.90.

### Is Codestral or Qwen2.5 7B Instruct better for coding?

Qwen2.5 7B Instruct scores higher on coding benchmarks: 35.9 versus 26.9 in the Noometry coding category.

### Which has the bigger context window?

Codestral does, with 256K tokens against 131K.

### How many benchmarks do Codestral and Qwen2.5 7B Instruct share?

2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Qwen2.5 7B Instruct has 15.