Model comparison
Codestral vs Qwen3-VL 235B-A22B
Qwen3-VL 235B-A22B is the stronger model overall, scoring 42.5 to 30.1 on the Noometry Index. Codestral costs 2.7× less per token, which makes it the better buy when Qwen3-VL 235B-A22B's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- The widest gap is in coding, where Qwen3-VL 235B-A22B leads 41.8 to 26.9.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.70 / $2.80 for Qwen3-VL 235B-A22B.
- Codestral accepts more context: 256K tokens versus 131K.
Side by side
| Codestral | Qwen3-VL 235B-A22B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.1 | 42.5 |
| Released | 2024-05-29 | 2025-04 |
| Weights | Open | Open |
| Context window | 256K | 131K |
| Max output | 4K | 33K |
| Input $ / M tokens | $0.30 | $0.70 |
| Output $ / M tokens | $0.90 | $2.80 |
| Results tracked | 7 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-VL 235B-A22B leads
Codestral: 26.9 (#316), Qwen3-VL 235B-A22B: 41.8 (#103)
| Benchmark | Codestral | Qwen3-VL 235B-A22B |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1438 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Qwen3-VL 235B-A22B leads
Codestral: 19.1 (#244), Qwen3-VL 235B-A22B: 28.1 (#92)
| Benchmark | Codestral | Qwen3-VL 235B-A22B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1428 |
Math Not comparable
Codestral: —, Qwen3-VL 235B-A22B: 36.2 (#120)
| Benchmark | Codestral | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Math | — | 1426 |
Knowledge Not comparable
Codestral: —, Qwen3-VL 235B-A22B: 39.6 (#120)
| Benchmark | Codestral | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Expert | — | 1440 |
Multimodal Not comparable
Codestral: —, Qwen3-VL 235B-A22B: 39.1 (#50)
| Benchmark | Codestral | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual Not comparable
Codestral: —, Qwen3-VL 235B-A22B: 52.1 (#92)
| Benchmark | Codestral | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Non-English | — | 1405 |
| LMArena Chinese | — | 1462 |
| LMArena French | — | 1448 |
| LMArena German | — | 1424 |
| LMArena Japanese | — | 1385 |
| LMArena Korean | — | 1395 |
| LMArena Russian | — | 1409 |
| LMArena Spanish | — | 1427 |
Instruction Following Not comparable
Codestral: —, Qwen3-VL 235B-A22B: 74.4 (#95)
| Benchmark | Codestral | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Instruction Following | — | 1407 |
Long Context Not comparable
Codestral: —, Qwen3-VL 235B-A22B: 43.4 (#93)
| Benchmark | Codestral | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Longer Query | — | 1420 |
Writing & Preference Not comparable
Codestral: —, Qwen3-VL 235B-A22B: 60.4 (#94)
| Benchmark | Codestral | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Text | — | 1420 |
| LMArena Creative Writing | — | 1367 |
| LMArena Multi-Turn | — | 1428 |
Frequently asked questions
Is Codestral better than Qwen3-VL 235B-A22B?
Qwen3-VL 235B-A22B is the stronger model overall, scoring 42.5 to 30.1 on the Noometry Index. Codestral costs 2.7× less per token, which makes it the better buy when Qwen3-VL 235B-A22B's lead doesn't matter for your workload.
Which is cheaper, Codestral or Qwen3-VL 235B-A22B?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Qwen3-VL 235B-A22B lists at $0.70 and $2.80.
Is Codestral or Qwen3-VL 235B-A22B better for coding?
Qwen3-VL 235B-A22B scores higher on coding benchmarks: 41.8 versus 26.9 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-VL 235B-A22B share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Qwen3-VL 235B-A22B has 18.