Model comparison
Ministral 8B vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 27.8 on the Noometry Index. Ministral 8B costs 38× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Ministral 8B scores higher in 0 categories and Qwen3.7 Max in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Max leads 61.7 to 12.5.
- The biggest single-benchmark swing is GPQA Diamond: 27.1% for Ministral 8B and 90.9% for Qwen3.7 Max.
- Ministral 8B is cheaper at $0.10 / $0.10 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 128K.
- Ministral 8B has downloadable open weights; the other is API-only.
Side by side
| Ministral 8B | Qwen3.7 Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 27.8 | 51.4 |
| Released | 2024-10-01 | 2026-05-19 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.10 | $2.50 |
| Output $ / M tokens | $0.10 | $7.50 |
| Results tracked | 17 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Ministral 8B: 34.4 (#226), Qwen3.7 Max: 50.2 (#43)
| Benchmark | Ministral 8B | Qwen3.7 Max |
|---|---|---|
| LMArena Coding | 1202 | 1498 |
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Qwen3.7 Max leads
Ministral 8B: 16.2 (#140), Qwen3.7 Max: 21.8 (#129)
| Benchmark | Ministral 8B | Qwen3.7 Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
Ministral 8B: 17.7 (#279), Qwen3.7 Max: 48.4 (#36)
| Benchmark | Ministral 8B | Qwen3.7 Max |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1483 |
| DTBench | 45.7% | 92.3% |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| LMCA | — | 44% |
| Epoch Capabilities Index | — | 153.74 |
Math Qwen3.7 Max leads
Ministral 8B: 23.7 (#262), Qwen3.7 Max: 62.3 (#26)
| Benchmark | Ministral 8B | Qwen3.7 Max |
|---|---|---|
| LMArena Math | 1188 | 1488 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| MATH Level 5 | 14.9% | — |
Knowledge Qwen3.7 Max leads
Ministral 8B: 12.5 (#292), Qwen3.7 Max: 61.7 (#24)
| Benchmark | Ministral 8B | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 27.1% | 90.9% |
| LMArena Expert | 1170 | 1488 |
| SimpleQA Verified | — | 55.8% |
| Vectara Hallucination Rate | 7.4% | — |
Multilingual Qwen3.7 Max leads
Ministral 8B: 35.3 (#242), Qwen3.7 Max: 57.1 (#13)
| Benchmark | Ministral 8B | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1165 | 1475 |
| LMArena Chinese | 1193 | 1533 |
| LMArena Russian | 1195 | 1482 |
Instruction Following Qwen3.7 Max leads
Ministral 8B: 60.7 (#245), Qwen3.7 Max: 76.9 (#34)
| Benchmark | Ministral 8B | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1161 | 1460 |
Long Context Qwen3.7 Max leads
Ministral 8B: 36.7 (#222), Qwen3.7 Max: 45.4 (#34)
| Benchmark | Ministral 8B | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1212 | 1484 |
Writing & Preference Qwen3.7 Max leads
Ministral 8B: 39.8 (#241), Qwen3.7 Max: 65.2 (#52)
| Benchmark | Ministral 8B | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1191 | 1476 |
| LMArena Creative Writing | 1175 | 1450 |
| LMArena Multi-Turn | 1166 | 1482 |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is Ministral 8B better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 27.8 on the Noometry Index. Ministral 8B costs 38× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, Ministral 8B or Qwen3.7 Max?
Ministral 8B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is Ministral 8B or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 128K.
How many benchmarks do Ministral 8B and Qwen3.7 Max share?
14 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Qwen3.7 Max has 33.