Model comparison
Mistral vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 29.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Mistral scores higher in 1 category and Qwen1.5-110B in 7 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5-110B leads 31.2 to 16.6.
- Qwen1.5-110B has downloadable open weights; the other is API-only.
Side by side
| Mistral | Qwen1.5-110B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 29.9 | 34.2 |
| Released | — | 2024-04-25 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral: 33.8 (#250), Qwen1.5-110B: 33.0 (#264)
| Benchmark | Mistral | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1162 | 1184 |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
Reasoning Too close to call
Mistral: 22.2 (#200), Qwen1.5-110B: 22.7 (#189)
| Benchmark | Mistral | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1168 |
| ForecastBench | — | 57.7 |
Math Qwen1.5-110B leads
Mistral: 22.3 (#278), Qwen1.5-110B: 33.7 (#201)
| Benchmark | Mistral | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1180 | 1185 |
| Omni-MATH | 7.2% | — |
Knowledge Qwen1.5-110B leads
Mistral: 16.6 (#288), Qwen1.5-110B: 31.2 (#219)
| Benchmark | Mistral | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1125 | 1144 |
| MMLU-Pro | 27.7% | — |
| GPQA (HELM) | 30.3% | — |
Multilingual Too close to call
Mistral: 32.8 (#254), Qwen1.5-110B: 33.6 (#250)
| Benchmark | Mistral | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1129 | 1142 |
| LMArena Chinese | 1109 | 1206 |
| LMArena French | 1180 | 1151 |
| LMArena German | 1155 | 1123 |
| LMArena Japanese | 1013 | 1074 |
| LMArena Korean | 1032 | 1044 |
| LMArena Russian | 1168 | 1118 |
| LMArena Spanish | 1143 | 1142 |
Instruction Following Qwen1.5-110B leads
Mistral: 52.6 (#288), Qwen1.5-110B: 60.3 (#252)
| Benchmark | Mistral | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1152 | 1158 |
| IFEval | 56.8% | — |
Long Context Too close to call
Mistral: 35.0 (#245), Qwen1.5-110B: 35.1 (#242)
| Benchmark | Mistral | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1153 | 1157 |
Writing & Preference Too close to call
Mistral: 37.0 (#260), Qwen1.5-110B: 38.0 (#255)
| Benchmark | Mistral | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1165 | 1175 |
| LMArena Creative Writing | 1158 | 1148 |
| LMArena Multi-Turn | 1147 | 1160 |
| WildBench | 66% | — |
Frequently asked questions
Is Mistral better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 29.9 on the Noometry Index.
Is Mistral or Qwen1.5-110B better for coding?
They score almost the same on coding (33.8 vs 33.0); test both on your own repository before choosing.
How many benchmarks do Mistral and Qwen1.5-110B share?
17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Qwen1.5-110B has 20.