Model comparison
Mistral Medium 3.5 vs Qwen-14B
Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 30.8 on the Noometry Index.
Last verified . 11 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 6 categories and Qwen-14B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium 3.5 leads 58.6 to 27.8.
Side by side
| Mistral Medium 3.5 | Qwen-14B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 39.6 | 30.8 |
| Released | — | 2023-09-24 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 210K | — |
| Input $ / M tokens | $1.50 | — |
| Output $ / M tokens | $7.50 | — |
| Results tracked | 22 | 18 |
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), Qwen-14B: 30.6 (#283)
| Benchmark | Mistral Medium 3.5 | Qwen-14B |
|---|---|---|
| LMArena Coding | 1461 | 1072 |
| LMArena WebDev | 1263 | — |
Reasoning Qwen-14B leads
Mistral Medium 3.5: 16.6 (#290), Qwen-14B: 18.7 (#255)
| Benchmark | Mistral Medium 3.5 | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1436 | 1027 |
| Epoch Capabilities Index | 141.42 | 112.8 |
| Kagi LLM Benchmark | 41.4% | — |
| NYT Connections (extended) | 12.9% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Mistral Medium 3.5 leads
Mistral Medium 3.5: 36.4 (#113), Qwen-14B: 28.7 (#224)
| Benchmark | Mistral Medium 3.5 | Qwen-14B |
|---|---|---|
| LMArena Math | 1432 | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Mistral Medium 3.5: 39.3 (#123), Qwen-14B: —
| Benchmark | Mistral Medium 3.5 | Qwen-14B |
|---|---|---|
| LMArena Expert | 1431 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multimodal Not comparable
Mistral Medium 3.5: 37.6 (#64), Qwen-14B: —
| Benchmark | Mistral Medium 3.5 | Qwen-14B |
|---|---|---|
| LMArena Vision | 1222 | — |
Multilingual Mistral Medium 3.5 leads
Mistral Medium 3.5: 52.1 (#93), Qwen-14B: 27.7 (#270)
| Benchmark | Mistral Medium 3.5 | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1405 | 1042 |
| LMArena Chinese | 1443 | 1077 |
| LMArena French | 1448 | — |
| LMArena German | 1453 | — |
| LMArena Korean | 1387 | — |
| LMArena Russian | 1396 | — |
| LMArena Spanish | 1406 | — |
Instruction Following Mistral Medium 3.5 leads
Mistral Medium 3.5: 74.7 (#87), Qwen-14B: 52.6 (#284)
| Benchmark | Mistral Medium 3.5 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1414 | 1031 |
Long Context Mistral Medium 3.5 leads
Mistral Medium 3.5: 43.2 (#101), Qwen-14B: 31.3 (#276)
| Benchmark | Mistral Medium 3.5 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1414 | 1029 |
Writing & Preference Mistral Medium 3.5 leads
Mistral Medium 3.5: 58.6 (#113), Qwen-14B: 27.8 (#294)
| Benchmark | Mistral Medium 3.5 | Qwen-14B |
|---|---|---|
| LMArena Text | 1421 | 1051 |
| LMArena Creative Writing | 1372 | 1028 |
| LMArena Multi-Turn | 1423 | 1022 |
| EQ-Bench 4 | 993 | — |
Frequently asked questions
Is Mistral Medium 3.5 better than Qwen-14B?
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 Qwen-14B better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 35.7 versus 30.6 in the Noometry coding category.
How many benchmarks do Mistral Medium 3.5 and Qwen-14B share?
11 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Qwen-14B has 18.