Model comparison
Mistral 7B vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 23.0 on the Noometry Index. Mistral 7B costs 15× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Max leads 62.4 to 8.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.3% for Mistral 7B and 95.6% for Qwen3.7 Max.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 8K.
- Mistral 7B has downloadable open weights; the other is API-only.
Side by side
| Mistral 7B | Qwen3.7 Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 23.0 | 51.5 |
| Released | 2023-09-27 | 2026-05-19 |
| Weights | Open | Proprietary |
| Context window | 8K | 1M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.25 | $2.50 |
| Output $ / M tokens | $0.25 | $7.50 |
| Results tracked | 37 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Mistral 7B: 26.4 (#326), Qwen3.7 Max: 50.4 (#45)
| Benchmark | Mistral 7B | Qwen3.7 Max |
|---|---|---|
| LMArena Coding | 1082 | 1498 |
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| BigCodeBench Instruct | 19.5% | — |
| BigCodeBench Complete | 27.3% | — |
| ALE-Bench | — | 1,189 |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Agentic & Tool Use Not comparable
Mistral 7B: —, Qwen3.7 Max: 22.1 (#135)
| Benchmark | Mistral 7B | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
Mistral 7B: 13.1 (#336), Qwen3.7 Max: 49.2 (#38)
| Benchmark | Mistral 7B | Qwen3.7 Max |
|---|---|---|
| Chess Puzzles | 0% | 19% |
| LMArena Hard Prompts | 1067 | 1483 |
| DTBench | 42.5% | 92.3% |
| Epoch Capabilities Index | 112.21 | 153.68 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| LMCA | — | 44% |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| HellaSwag | 81% | — |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math Qwen3.7 Max leads
Mistral 7B: 8.1 (#325), Qwen3.7 Max: 62.4 (#32)
| Benchmark | Mistral 7B | Qwen3.7 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.3% | 95.6% |
| LMArena Math | 1085 | 1490 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| ProofBench | — | 26% |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |
Knowledge Qwen3.7 Max leads
Mistral 7B: 7.4 (#311), Qwen3.7 Max: 61.6 (#28)
| Benchmark | Mistral 7B | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 15.2% | 90.9% |
| LMArena Expert | 1036 | 1488 |
| SimpleQA Verified | — | 55.8% |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| MMLU | 62.5% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual Qwen3.7 Max leads
Mistral 7B: 25.8 (#283), Qwen3.7 Max: 56.9 (#15)
| Benchmark | Mistral 7B | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1012 | 1474 |
| LMArena Chinese | 1009 | 1530 |
| LMArena Russian | 1018 | 1484 |
| LMArena French | 1037 | — |
| LMArena German | 987 | — |
| LMArena Japanese | 878 | — |
| LMArena Spanish | 1026 | — |
Instruction Following Qwen3.7 Max leads
Mistral 7B: 54.2 (#280), Qwen3.7 Max: 76.7 (#38)
| Benchmark | Mistral 7B | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1060 | 1460 |
Long Context Qwen3.7 Max leads
Mistral 7B: 32.2 (#271), Qwen3.7 Max: 45.4 (#40)
| Benchmark | Mistral 7B | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1060 | 1482 |
Writing & Preference Qwen3.7 Max leads
Mistral 7B: 30.7 (#286), Qwen3.7 Max: 65.0 (#54)
| Benchmark | Mistral 7B | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1090 | 1476 |
| LMArena Creative Writing | 1068 | 1449 |
| LMArena Multi-Turn | 1062 | 1481 |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is Mistral 7B better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 23.0 on the Noometry Index. Mistral 7B costs 15× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, Mistral 7B or Qwen3.7 Max?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is Mistral 7B or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 8K.
How many benchmarks do Mistral 7B and Qwen3.7 Max share?
17 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Qwen3.7 Max has 33.