Model comparison
Codestral vs Qwen2.5 7B Instruct
Codestral is the stronger model overall, scoring 30.6 to 29.0 on the Noometry Index.
Last verified . 2 shared benchmarks.
Mistral AI
Alibaba (Qwen)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 36.5 to 27.3.
- 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.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| Codestral | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.6 | 29.0 |
| Released | 2024-05-29 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 256K | 131K |
| Max output | 8K | 8K |
| Input $ / M tokens | $0.30 | $0.17 |
| Output $ / M tokens | $0.90 | $0.70 |
| Results tracked | 7 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
Codestral: 27.3 (#321), Qwen2.5 7B Instruct: 36.5 (#208)
| 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 Not comparable
Codestral: —, Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Codestral leads
Codestral: 19.8 (#251), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| Epoch Capabilities Index | — | 118.51 |
Math Not comparable
Codestral: —, Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
Knowledge Not comparable
Codestral: —, Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| MMLU | — | 72.9% |
Instruction Following Not comparable
Codestral: —, Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
Writing & Preference Not comparable
Codestral: —, Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Codestral | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | — | 73.1% |
Frequently asked questions
Is Codestral better than Qwen2.5 7B Instruct?
Codestral is the stronger model overall, scoring 30.6 to 29.0 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: 36.5 versus 27.3 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.