Model comparison
Codestral vs Qwen3-1.7B
Codestral is the stronger model overall, scoring 30.6 to 26.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- Qwen3-1.7B has downloadable open weights; the other is API-only.
Side by side
| Codestral | Qwen3-1.7B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.6 | 26.6 |
| Released | 2024-05-29 | 2025-04-29 |
| Weights | Proprietary | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Codestral: 27.3 (#321), Qwen3-1.7B: —
| Benchmark | Codestral | Qwen3-1.7B |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, Qwen3-1.7B: 24.7 (#115)
| Benchmark | Codestral | Qwen3-1.7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.4% |
Reasoning Too close to call
Codestral: 19.8 (#251), Qwen3-1.7B: 19.2 (#267)
| Benchmark | Codestral | Qwen3-1.7B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| Chess Puzzles | — | 0% |
Math Not comparable
Codestral: —, Qwen3-1.7B: 16.3 (#294)
| Benchmark | Codestral | Qwen3-1.7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
Knowledge Not comparable
Codestral: —, Qwen3-1.7B: 19.6 (#278)
| Benchmark | Codestral | Qwen3-1.7B |
|---|---|---|
| GPQA Diamond | — | 38% |
Frequently asked questions
Is Codestral better than Qwen3-1.7B?
Codestral is the stronger model overall, scoring 30.6 to 26.6 on the Noometry Index.
How many benchmarks do Codestral and Qwen3-1.7B share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Qwen3-1.7B has 4.