Model comparison
Codestral vs Qwen Turbo
Codestral is the stronger model overall, scoring 30.6 to 27.1 on the Noometry Index. Qwen Turbo costs 5.1× less per token, which makes it the better buy when Codestral's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- Qwen Turbo is cheaper at $0.05 / $0.20 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Qwen Turbo accepts more context: 1M tokens versus 256K.
Side by side
| Codestral | Qwen Turbo | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.6 | 27.1 |
| Released | 2024-05-29 | 2024-11-01 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | 1M |
| Max output | 8K | 16K |
| Input $ / M tokens | $0.30 | $0.05 |
| Output $ / M tokens | $0.90 | $0.20 |
| Results tracked | 7 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Codestral: 27.3 (#321), Qwen Turbo: —
| Benchmark | Codestral | Qwen Turbo |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Not comparable
Codestral: 19.8 (#251), Qwen Turbo: —
| Benchmark | Codestral | Qwen Turbo |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
Math Not comparable
Codestral: —, Qwen Turbo: 15.3 (#297)
| Benchmark | Codestral | Qwen Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 6.1% |
| MATH Level 5 | — | 56.2% |
Knowledge Not comparable
Codestral: —, Qwen Turbo: 22.2 (#272)
| Benchmark | Codestral | Qwen Turbo |
|---|---|---|
| GPQA Diamond | — | 41.8% |
Frequently asked questions
Is Codestral better than Qwen Turbo?
Codestral is the stronger model overall, scoring 30.6 to 27.1 on the Noometry Index. Qwen Turbo costs 5.1× less per token, which makes it the better buy when Codestral's lead doesn't matter for your workload.
Which is cheaper, Codestral or Qwen Turbo?
Qwen Turbo is cheaper. It lists at $0.05 per million input tokens and $0.20 per million output tokens; Codestral lists at $0.30 and $0.90.
Which has the bigger context window?
Qwen Turbo does, with 1M tokens against 256K.
How many benchmarks do Codestral and Qwen Turbo share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Qwen Turbo has 3.