Model comparison
Mistral Large 3 vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 38.6 on the Noometry Index. Mistral Large 3 costs 1.9× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Mistral Large 3 scores higher in 0 categories and Qwen3.7 Plus in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Plus leads 38.4 to 14.6.
- The biggest single-benchmark swing is NYT Connections (extended): 7.5% for Mistral Large 3 and 74.8% for Qwen3.7 Plus.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 Plus accepts more context: 1M tokens versus 262K.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Large 3 | Qwen3.7 Plus | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 38.6 | 45.0 |
| Released | 2025-12-02 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.25 | $0.40 |
| Output $ / M tokens | $0.75 | $1.60 |
| Results tracked | 24 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Plus leads
Mistral Large 3: 34.1 (#230), Qwen3.7 Plus: 36.1 (#200)
| Benchmark | Mistral Large 3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1447 | 1473 |
| FrontierCode | — | 10.2% |
| LMArena WebDev | 1230 | — |
| SciCode | — | 45.5% |
Agentic & Tool Use Not comparable
Mistral Large 3: —, Qwen3.7 Plus: 21.2 (#130)
| Benchmark | Mistral Large 3 | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
Mistral Large 3: 14.6 (#314), Qwen3.7 Plus: 38.4 (#54)
| Benchmark | Mistral Large 3 | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 7.5% | 74.8% |
| LMArena Hard Prompts | 1429 | 1460 |
| Kagi LLM Benchmark | 50.9% | — |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | 23% | — |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 147.39 |
Math Qwen3.7 Plus leads
Mistral Large 3: 36.0 (#131), Qwen3.7 Plus: 49.3 (#47)
| Benchmark | Mistral Large 3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1415 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
Knowledge Qwen3.7 Plus leads
Mistral Large 3: 35.5 (#173), Qwen3.7 Plus: 54.9 (#46)
| Benchmark | Mistral Large 3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Expert | 1421 | 1467 |
| GPQA Diamond | — | 87.9% |
| Vectara Hallucination Rate | 14.5% | — |
Multimodal Qwen3.7 Plus leads
Mistral Large 3: 37.6 (#65), Qwen3.7 Plus: 41.2 (#30)
| Benchmark | Mistral Large 3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1222 | 1281 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
Mistral Large 3: 52.6 (#79), Qwen3.7 Plus: 55.0 (#36)
| Benchmark | Mistral Large 3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1412 | 1445 |
| LMArena Chinese | 1448 | 1510 |
| LMArena French | 1456 | 1471 |
| LMArena German | 1438 | 1471 |
| LMArena Japanese | 1399 | 1411 |
| LMArena Korean | 1384 | 1416 |
| LMArena Russian | 1412 | 1457 |
| LMArena Spanish | 1437 | 1453 |
Instruction Following Qwen3.7 Plus leads
Mistral Large 3: 74.1 (#104), Qwen3.7 Plus: 75.9 (#49)
| Benchmark | Mistral Large 3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1402 | 1439 |
Long Context Qwen3.7 Plus leads
Mistral Large 3: 43.1 (#102), Qwen3.7 Plus: 44.5 (#61)
| Benchmark | Mistral Large 3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1413 | 1454 |
Writing & Preference Qwen3.7 Plus leads
Mistral Large 3: 60.2 (#100), Qwen3.7 Plus: 64.5 (#54)
| Benchmark | Mistral Large 3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1427 | 1454 |
| LMArena Creative Writing | 1385 | 1439 |
| LMArena Multi-Turn | 1429 | 1459 |
| EQ-Bench Creative Writing | 1412 | — |
Frequently asked questions
Is Mistral Large 3 better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 38.6 on the Noometry Index. Mistral Large 3 costs 1.9× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Which is cheaper, Mistral Large 3 or Qwen3.7 Plus?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is Mistral Large 3 or Qwen3.7 Plus better for coding?
Qwen3.7 Plus scores higher on coding benchmarks: 36.1 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 262K.
How many benchmarks do Mistral Large 3 and Qwen3.7 Plus share?
19 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Qwen3.7 Plus has 32.