Model comparison
Mistral Medium 3.5 vs Qwen1.5-7B
Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 30.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 7 categories and Qwen1.5-7B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium 3.5 leads 58.6 to 29.8.
Side by side
| Mistral Medium 3.5 | Qwen1.5-7B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 39.6 | 30.8 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 210K | — |
| Input $ / M tokens | $1.50 | — |
| Output $ / M tokens | $7.50 | — |
| Results tracked | 22 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium 3.5 leads
Mistral Medium 3.5: 35.7 (#208), Qwen1.5-7B: 31.6 (#271)
| Benchmark | Mistral Medium 3.5 | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1461 | 1107 |
| LMArena WebDev | 1263 | — |
Reasoning Qwen1.5-7B leads
Mistral Medium 3.5: 16.6 (#290), Qwen1.5-7B: 19.5 (#237)
| Benchmark | Mistral Medium 3.5 | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1436 | 1066 |
| Kagi LLM Benchmark | 41.4% | — |
| NYT Connections (extended) | 12.9% | — |
| Epoch Capabilities Index | 141.42 | — |
Math Mistral Medium 3.5 leads
Mistral Medium 3.5: 36.4 (#113), Qwen1.5-7B: 29.0 (#222)
| Benchmark | Mistral Medium 3.5 | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1432 | 1080 |
Knowledge Mistral Medium 3.5 leads
Mistral Medium 3.5: 39.3 (#123), Qwen1.5-7B: 28.2 (#239)
| Benchmark | Mistral Medium 3.5 | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 1431 | 1055 |
| MMLU | — | 62.6% |
Multimodal Not comparable
Mistral Medium 3.5: 37.6 (#64), Qwen1.5-7B: —
| Benchmark | Mistral Medium 3.5 | Qwen1.5-7B |
|---|---|---|
| LMArena Vision | 1222 | — |
Multilingual Mistral Medium 3.5 leads
Mistral Medium 3.5: 52.1 (#93), Qwen1.5-7B: 28.6 (#266)
| Benchmark | Mistral Medium 3.5 | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1405 | 1058 |
| LMArena Chinese | 1443 | 1140 |
| LMArena Russian | 1396 | 1006 |
| LMArena French | 1448 | — |
| LMArena German | 1453 | — |
| LMArena Korean | 1387 | — |
| LMArena Spanish | 1406 | — |
Instruction Following Mistral Medium 3.5 leads
Mistral Medium 3.5: 74.7 (#87), Qwen1.5-7B: 54.4 (#276)
| Benchmark | Mistral Medium 3.5 | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1414 | 1058 |
Long Context Mistral Medium 3.5 leads
Mistral Medium 3.5: 43.2 (#101), Qwen1.5-7B: 33.1 (#261)
| Benchmark | Mistral Medium 3.5 | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1414 | 1090 |
Writing & Preference Mistral Medium 3.5 leads
Mistral Medium 3.5: 58.6 (#113), Qwen1.5-7B: 29.8 (#288)
| Benchmark | Mistral Medium 3.5 | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1421 | 1084 |
| LMArena Creative Writing | 1372 | 1035 |
| LMArena Multi-Turn | 1423 | 1061 |
| EQ-Bench 4 | 993 | — |
Frequently asked questions
Is Mistral Medium 3.5 better than Qwen1.5-7B?
Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 30.8 on the Noometry Index.
Is Mistral Medium 3.5 or Qwen1.5-7B better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 35.7 versus 31.6 in the Noometry coding category.
How many benchmarks do Mistral Medium 3.5 and Qwen1.5-7B share?
12 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Qwen1.5-7B has 13.