Model comparison
Codestral vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 30.6 on the Noometry Index. Codestral costs 6.7× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where Qwen3.8 Max leads 54.4 to 19.8.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 256K.
Side by side
| Codestral | Qwen3.8 Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.6 | 56.8 |
| Released | 2024-05-29 | 2026-08-02 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | 1M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.30 | $2 |
| Output $ / M tokens | $0.90 | $6 |
| Results tracked | 7 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Codestral: 27.3 (#321), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Codestral | Qwen3.8 Max |
|---|---|---|
| DeepSWE | — | 57.5% |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1502 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | Codestral | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Codestral: 19.8 (#251), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Codestral | Qwen3.8 Max |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| LMArena Hard Prompts | — | 1496 |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |
Math Not comparable
Codestral: —, Qwen3.8 Max: 73.2 (#20)
| Benchmark | Codestral | Qwen3.8 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
| LMArena Math | — | 1499 |
Knowledge Not comparable
Codestral: —, Qwen3.8 Max: 61.7 (#27)
| Benchmark | Codestral | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| LMArena Expert | — | 1507 |
Multimodal Not comparable
Codestral: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Codestral | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Not comparable
Codestral: —, Qwen3.8 Max: 56.7 (#18)
| Benchmark | Codestral | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | — | 1472 |
| LMArena Chinese | — | 1538 |
| LMArena French | — | 1503 |
| LMArena German | — | 1483 |
| LMArena Japanese | — | 1467 |
| LMArena Korean | — | 1461 |
| LMArena Russian | — | 1481 |
| LMArena Spanish | — | 1492 |
Instruction Following Not comparable
Codestral: —, Qwen3.8 Max: 77.6 (#17)
| Benchmark | Codestral | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | — | 1479 |
Long Context Not comparable
Codestral: —, Qwen3.8 Max: 45.6 (#31)
| Benchmark | Codestral | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | — | 1489 |
Writing & Preference Not comparable
Codestral: —, Qwen3.8 Max: 67.1 (#30)
| Benchmark | Codestral | Qwen3.8 Max |
|---|---|---|
| LMArena Text | — | 1483 |
| LMArena Creative Writing | — | 1479 |
| LMArena Multi-Turn | — | 1489 |
Frequently asked questions
Is Codestral better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 30.6 on the Noometry Index. Codestral costs 6.7× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, Codestral or Qwen3.8 Max?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is Codestral or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 256K.
How many benchmarks do Codestral and Qwen3.8 Max share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Qwen3.8 Max has 39.