Model comparison
Mistral Small 3 vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 31.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Mistral Small 3 scores higher in 4 categories and Qwen1.5-110B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-110B leads 33.7 to 16.3.
- The biggest single-benchmark swing is BigCodeBench Instruct: 45.3% for Mistral Small 3 and 35% for Qwen1.5-110B.
Side by side
| Mistral Small 3 | Qwen1.5-110B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.2 | 34.2 |
| Released | 2025-01-30 | 2024-04-25 |
| Weights | Open | Open |
| Context window | 33K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 24 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
Mistral Small 3: 36.5 (#207), Qwen1.5-110B: 33.0 (#264)
| Benchmark | Mistral Small 3 | Qwen1.5-110B |
|---|---|---|
| BigCodeBench Instruct | 45.3% | 35% |
| LMArena Coding | 1246 | 1184 |
| BigCodeBench Complete | 50.4% | 44.4% |
Reasoning Qwen1.5-110B leads
Mistral Small 3: 18.9 (#273), Qwen1.5-110B: 22.7 (#189)
| Benchmark | Mistral Small 3 | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1168 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 127.07 | — |
| ForecastBench | — | 57.7 |
Math Qwen1.5-110B leads
Mistral Small 3: 16.3 (#295), Qwen1.5-110B: 33.7 (#201)
| Benchmark | Mistral Small 3 | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1240 | 1185 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
Knowledge Qwen1.5-110B leads
Mistral Small 3: 25.1 (#263), Qwen1.5-110B: 31.2 (#219)
| Benchmark | Mistral Small 3 | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1202 | 1144 |
| GPQA Diamond | 47.3% | — |
| Confabulations | 25.2% | — |
Multilingual Mistral Small 3 leads
Mistral Small 3: 37.3 (#236), Qwen1.5-110B: 33.6 (#250)
| Benchmark | Mistral Small 3 | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1198 | 1142 |
| LMArena Chinese | 1204 | 1206 |
| LMArena French | 1203 | 1151 |
| LMArena German | 1211 | 1123 |
| LMArena Japanese | 1111 | 1074 |
| LMArena Korean | 1188 | 1044 |
| LMArena Russian | 1216 | 1118 |
| LMArena Spanish | — | 1142 |
Instruction Following Mistral Small 3 leads
Mistral Small 3: 63.7 (#229), Qwen1.5-110B: 60.3 (#252)
| Benchmark | Mistral Small 3 | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1214 | 1158 |
Long Context Mistral Small 3 leads
Mistral Small 3: 37.8 (#211), Qwen1.5-110B: 35.1 (#242)
| Benchmark | Mistral Small 3 | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1246 | 1157 |
Writing & Preference Qwen1.5-110B leads
Mistral Small 3: 32.2 (#280), Qwen1.5-110B: 38.0 (#255)
| Benchmark | Mistral Small 3 | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1234 | 1175 |
| LMArena Creative Writing | 1195 | 1148 |
| LMArena Multi-Turn | 1217 | 1160 |
| EQ-Bench Creative Writing | 707 | — |
Frequently asked questions
Is Mistral Small 3 better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 31.2 on the Noometry Index.
Is Mistral Small 3 or Qwen1.5-110B better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 33.0 in the Noometry coding category.
How many benchmarks do Mistral Small 3 and Qwen1.5-110B share?
18 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen1.5-110B has 20.