Model comparison
Ministral 8B vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.1 to 27.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Ministral 8B scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5-Max leads 34.8 to 12.5.
- Ministral 8B has downloadable open weights; the other is API-only.
Side by side
| Ministral 8B | Qwen2.5-Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 27.8 | 40.1 |
| Released | 2024-10-01 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.10 | — |
| Results tracked | 17 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Ministral 8B: 34.4 (#226), Qwen2.5-Max: 41.2 (#118)
| Benchmark | Ministral 8B | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1202 | 1359 |
| LiveBench Coding | — | 64.4% |
Agentic & Tool Use Not comparable
Ministral 8B: 16.2 (#140), Qwen2.5-Max: —
| Benchmark | Ministral 8B | Qwen2.5-Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
Reasoning Qwen2.5-Max leads
Ministral 8B: 17.7 (#279), Qwen2.5-Max: 24.6 (#144)
| Benchmark | Ministral 8B | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1360 |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 45.7% | — |
| LiveBench Data Analysis | — | 67.9% |
| Epoch Capabilities Index | — | 132.54 |
| LiveBench | — | 62.3% |
Math Qwen2.5-Max leads
Ministral 8B: 23.7 (#262), Qwen2.5-Max: 34.3 (#162)
| Benchmark | Ministral 8B | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1188 | 1369 |
| LiveBench Math | — | 58.4% |
| MATH Level 5 | 14.9% | — |
Knowledge Qwen2.5-Max leads
Ministral 8B: 12.5 (#292), Qwen2.5-Max: 34.8 (#181)
| Benchmark | Ministral 8B | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1170 | 1337 |
| GPQA Diamond | 27.1% | — |
| Confabulations | — | 21.8% |
| Vectara Hallucination Rate | 7.4% | — |
Multilingual Qwen2.5-Max leads
Ministral 8B: 35.3 (#242), Qwen2.5-Max: 48.3 (#140)
| Benchmark | Ministral 8B | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1165 | 1352 |
| LMArena Chinese | 1193 | 1382 |
| LMArena Russian | 1195 | 1353 |
| LMArena French | — | 1396 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1299 |
| LMArena Korean | — | 1304 |
| LMArena Spanish | — | 1377 |
Instruction Following Qwen2.5-Max leads
Ministral 8B: 60.7 (#245), Qwen2.5-Max: 71.5 (#147)
| Benchmark | Ministral 8B | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1161 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Qwen2.5-Max leads
Ministral 8B: 36.7 (#222), Qwen2.5-Max: 41.3 (#137)
| Benchmark | Ministral 8B | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1212 | 1358 |
Writing & Preference Qwen2.5-Max leads
Ministral 8B: 39.8 (#241), Qwen2.5-Max: 55.6 (#141)
| Benchmark | Ministral 8B | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1191 | 1367 |
| LMArena Creative Writing | 1175 | 1339 |
| LMArena Multi-Turn | 1166 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Ministral 8B better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.1 to 27.8 on the Noometry Index.
Is Ministral 8B or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.2 versus 34.4 in the Noometry coding category.
How many benchmarks do Ministral 8B and Qwen2.5-Max share?
12 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Qwen2.5-Max has 27.