Model comparison
Codestral vs Qwen3-Coder 480B-A35B Instruct
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 30.6 on the Noometry Index. Codestral costs 6.7× less per token, which makes it the better buy when Qwen3-Coder 480B-A35B Instruct's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. Codestral scores higher in 0 categories and Qwen3-Coder 480B-A35B Instruct in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen3-Coder 480B-A35B Instruct leads 35.5 to 27.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 32.5% for Codestral and 49.5% for Qwen3-Coder 480B-A35B Instruct.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 256K.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.
Side by side
| Codestral | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.6 | 38.1 |
| Released | 2024-05-29 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 256K | 262K |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.30 | $1.50 |
| Output $ / M tokens | $0.90 | $7.50 |
| Results tracked | 7 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Coder 480B-A35B Instruct leads
Codestral: 27.3 (#321), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | Codestral | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| ALE-Bench | 137.78 | 461.45 |
| SWE-bench Verified (bash only) | — | 55.4% |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1275 |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1412 |
| BigCodeBench Complete | 52.5% | — |
| AlgoTune | — | 1.44 |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | Codestral | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
Codestral: 19.8 (#251), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | Codestral | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 49.5% |
| LMArena Hard Prompts | — | 1372 |
Math Not comparable
Codestral: —, Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | Codestral | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | — | 1365 |
Knowledge Not comparable
Codestral: —, Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | Codestral | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | — | 1338 |
Multilingual Not comparable
Codestral: —, Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | Codestral | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | — | 1346 |
| LMArena Chinese | — | 1357 |
| LMArena French | — | 1398 |
| LMArena German | — | 1325 |
| LMArena Japanese | — | 1310 |
| LMArena Korean | — | 1305 |
| LMArena Russian | — | 1366 |
| LMArena Spanish | — | 1360 |
Instruction Following Not comparable
Codestral: —, Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | Codestral | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1355 |
Long Context Not comparable
Codestral: —, Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | Codestral | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | — | 1378 |
Writing & Preference Not comparable
Codestral: —, Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | Codestral | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | — | 1357 |
| LMArena Creative Writing | — | 1333 |
| LMArena Multi-Turn | — | 1365 |
Frequently asked questions
Is Codestral better than Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 30.6 on the Noometry Index. Codestral costs 6.7× less per token, which makes it the better buy when Qwen3-Coder 480B-A35B Instruct's lead doesn't matter for your workload.
Which is cheaper, Codestral or Qwen3-Coder 480B-A35B Instruct?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is Codestral or Qwen3-Coder 480B-A35B Instruct better for coding?
Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 35.5 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 256K.
How many benchmarks do Codestral and Qwen3-Coder 480B-A35B Instruct share?
2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.