Model comparison
Codestral vs Qwen3 8B
Qwen3 8B is the stronger model overall, scoring 33.7 to 30.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- The widest gap is in coding, where Qwen3 8B leads 34.0 to 27.3.
- Qwen3 8B is cheaper at $0.18 / $0.70 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Codestral accepts more context: 256K tokens versus 131K.
- Qwen3 8B has downloadable open weights; the other is API-only.
Side by side
| Codestral | Qwen3 8B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.6 | 33.7 |
| Released | 2024-05-29 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 256K | 131K |
| Max output | 8K | 8K |
| Input $ / M tokens | $0.30 | $0.18 |
| Output $ / M tokens | $0.90 | $0.70 |
| Results tracked | 7 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 8B leads
Codestral: 27.3 (#321), Qwen3 8B: 34.0 (#248)
| Benchmark | Codestral | Qwen3 8B |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| SciCode | — | 22.6% |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, Qwen3 8B: 30.2 (#78)
| Benchmark | Codestral | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |
Reasoning Codestral leads
Codestral: 19.8 (#251), Qwen3 8B: 16.6 (#303)
| Benchmark | Codestral | Qwen3 8B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 5% |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |
| Epoch Capabilities Index | — | 136.17 |
Math Not comparable
Codestral: —, Qwen3 8B: 34.9 (#191)
| Benchmark | Codestral | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 56.1% |
Knowledge Not comparable
Codestral: —, Qwen3 8B: 36.1 (#173)
| Benchmark | Codestral | Qwen3 8B |
|---|---|---|
| GPQA Diamond | — | 56.8% |
| Vectara Hallucination Rate | — | 4.8% |
Long Context Not comparable
Codestral: —, Qwen3 8B: 37.9 (#210)
| Benchmark | Codestral | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
Frequently asked questions
Is Codestral better than Qwen3 8B?
Qwen3 8B is the stronger model overall, scoring 33.7 to 30.6 on the Noometry Index.
Which is cheaper, Codestral or Qwen3 8B?
Qwen3 8B is cheaper. It lists at $0.18 per million input tokens and $0.70 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Codestral or Qwen3 8B better for coding?
Qwen3 8B scores higher on coding benchmarks: 34.0 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 Qwen3 8B share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Qwen3 8B has 11.