Model comparison
Mistral Large vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 31.9 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Qwen3.8 Max in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Mistral Large and 100% for Qwen3.8 Max.
- Both cost about the same: $2 input and $6 output per million tokens.
- Qwen3.8 Max accepts more context: 1M tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large | Qwen3.8 Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.9 | 56.8 |
| Released | 2024-02-26 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 16K | 131K |
| Input $ / M tokens | $2 | $2 |
| Output $ / M tokens | $6 | $6 |
| Results tracked | 51 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Mistral Large: 34.3 (#240), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Mistral Large | Qwen3.8 Max |
|---|---|---|
| SciCode | 36.2% | 53.2% |
| LMArena Coding | 1277 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Qwen3.8 Max leads
Mistral Large: 28.6 (#89), Qwen3.8 Max: 45.4 (#14)
| Benchmark | Mistral Large | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| Berkeley Function Calling Leaderboard | 38.4% | — |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Mistral Large: 15.8 (#310), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Mistral Large | Qwen3.8 Max |
|---|---|---|
| CritPt | 0% | 20% |
| LMArena Hard Prompts | 1257 | 1496 |
| DTBench | 65.1% | 92% |
| LMCA | 16.7% | 46.2% |
| Epoch Capabilities Index | 128.52 | 156.41 |
| SimpleBench | 22.5% | — |
| NYT Connections (extended) | — | 88.3% |
| Chess Puzzles | — | 40% |
| LiveBench Reasoning | 43.5% | — |
| Mystery Game Puzzles | — | 38% |
| LiveBench Data Analysis | 50.1% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Qwen3.8 Max leads
Mistral Large: 18.2 (#291), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Mistral Large | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 100% |
| LMArena Math | 1262 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3.8 Max leads
Mistral Large: 30.1 (#230), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Mistral Large | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 51.3% | 92.7% |
| LMArena Expert | 1232 | 1507 |
| SimpleQA Verified | — | 47.3% |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multimodal Not comparable
Mistral Large: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Mistral Large | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
Mistral Large: 40.0 (#219), Qwen3.8 Max: 56.7 (#18)
| Benchmark | Mistral Large | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1237 | 1472 |
| LMArena Chinese | 1240 | 1538 |
| LMArena French | 1325 | 1503 |
| LMArena German | 1254 | 1483 |
| LMArena Japanese | 1188 | 1467 |
| LMArena Korean | 1202 | 1461 |
| LMArena Russian | 1257 | 1481 |
| LMArena Spanish | 1268 | 1492 |
Instruction Following Qwen3.8 Max leads
Mistral Large: 67.9 (#191), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Mistral Large | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1249 | 1479 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Qwen3.8 Max leads
Mistral Large: 38.3 (#199), Qwen3.8 Max: 45.6 (#31)
| Benchmark | Mistral Large | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1261 | 1489 |
Writing & Preference Qwen3.8 Max leads
Mistral Large: 40.7 (#242), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Mistral Large | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1266 | 1483 |
| LMArena Creative Writing | 1243 | 1479 |
| LMArena Multi-Turn | 1260 | 1489 |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 31.9 on the Noometry Index.
Which is cheaper, Mistral Large or Qwen3.8 Max?
Qwen3.8 Max is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 131K.
How many benchmarks do Mistral Large and Qwen3.8 Max share?
24 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen3.8 Max has 39.