Model comparison
Mistral Large 4 vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 43.1 on the Noometry Index. Mistral Large 4 costs 2.9× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. Mistral Large 4 scores higher in 0 categories and Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 40.4.
- The biggest single-benchmark swing is NYT Connections (extended): 27.4% for Mistral Large 4 and 88.3% for Qwen3.8 Max.
- Mistral Large 4 is cheaper at $0.68 / $2.09 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Mistral Large 4 accepts more context: 1.05M tokens versus 1M.
Side by side
| Mistral Large 4 | Qwen3.8 Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 43.1 | 56.8 |
| Released | 2026-10-06 | 2026-08-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 262K | 131K |
| Input $ / M tokens | $0.68 | $2 |
| Output $ / M tokens | $2.09 | $6 |
| Results tracked | 15 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Mistral Large 4: 48.6 (#57), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Mistral Large 4 | Qwen3.8 Max |
|---|---|---|
| LMArena WebDev | 1541 | 1674 |
| LMArena Coding | 1475 | 1502 |
| DeepSWE | — | 57.5% |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
Agentic & Tool Use Not comparable
Mistral Large 4: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | Mistral Large 4 | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Mistral Large 4: 22.5 (#192), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Mistral Large 4 | Qwen3.8 Max |
|---|---|---|
| NYT Connections (extended) | 27.4% | 88.3% |
| LMArena Hard Prompts | 1444 | 1496 |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |
Math Qwen3.8 Max leads
Mistral Large 4: 40.4 (#91), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Mistral Large 4 | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1488 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
Knowledge Qwen3.8 Max leads
Mistral Large 4: 36.6 (#166), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Mistral Large 4 | Qwen3.8 Max |
|---|---|---|
| SimpleQA Verified | 20% | 47.3% |
| LMArena Expert | 1447 | 1507 |
| GPQA Diamond | — | 92.7% |
Multimodal Not comparable
Mistral Large 4: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Mistral Large 4 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
Mistral Large 4: 52.6 (#82), Qwen3.8 Max: 56.7 (#18)
| Benchmark | Mistral Large 4 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1415 | 1472 |
| LMArena Chinese | 1491 | 1538 |
| LMArena Russian | 1414 | 1481 |
| LMArena French | — | 1503 |
| LMArena German | — | 1483 |
| LMArena Japanese | — | 1467 |
| LMArena Korean | — | 1461 |
| LMArena Spanish | — | 1492 |
Instruction Following Qwen3.8 Max leads
Mistral Large 4: 75.0 (#76), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Mistral Large 4 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1424 | 1479 |
Long Context Qwen3.8 Max leads
Mistral Large 4: 43.6 (#89), Qwen3.8 Max: 45.6 (#31)
| Benchmark | Mistral Large 4 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1429 | 1489 |
Writing & Preference Qwen3.8 Max leads
Mistral Large 4: 60.4 (#97), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Mistral Large 4 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1427 | 1483 |
| LMArena Creative Writing | 1361 | 1479 |
| LMArena Multi-Turn | 1424 | 1489 |
Frequently asked questions
Is Mistral Large 4 better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 43.1 on the Noometry Index. Mistral Large 4 costs 2.9× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, Mistral Large 4 or Qwen3.8 Max?
Mistral Large 4 is cheaper. It lists at $0.68 per million input tokens and $2.09 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is Mistral Large 4 or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 48.6 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 4 does, with 1.05M tokens against 1M.
How many benchmarks do Mistral Large 4 and Qwen3.8 Max share?
15 benchmarks have published results for both models. Mistral Large 4 has 15 scored results on Noometry and Qwen3.8 Max has 39.