Model comparison
Magistral Small vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 33.6 to 29.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where Qwen1.5-110B leads 21.7 to 6.9.
Side by side
| Magistral Small | Qwen1.5-110B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 29.9 | 33.6 |
| Released | 2025-06-10 | 2024-04-25 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 40K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 10 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Small leads
Magistral Small: 37.8 (#172), Qwen1.5-110B: 32.4 (#260)
| Benchmark | Magistral Small | Qwen1.5-110B |
|---|---|---|
| SciCode | 35.2% | — |
| BigCodeBench Instruct | — | 35% |
| LMArena Coding | — | 1184 |
| BigCodeBench Complete | — | 44.4% |
Reasoning Qwen1.5-110B leads
Magistral Small: 6.9 (#345), Qwen1.5-110B: 21.7 (#192)
| Benchmark | Magistral Small | Qwen1.5-110B |
|---|---|---|
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 6.3% | — |
| ARC-AGI-1 | 5% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 3% | — |
| LMArena Hard Prompts | — | 1168 |
| DTBench | 61.3% | — |
| Epoch Capabilities Index | 133.19 | — |
| ForecastBench | — | 57.7 |
Math Qwen1.5-110B leads
Magistral Small: 24.9 (#253), Qwen1.5-110B: 31.1 (#199)
| Benchmark | Magistral Small | Qwen1.5-110B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | — |
| LMArena Math | — | 1185 |
Knowledge Too close to call
Magistral Small: 30.9 (#215), Qwen1.5-110B: 30.7 (#217)
| Benchmark | Magistral Small | Qwen1.5-110B |
|---|---|---|
| GPQA Diamond | 56.1% | — |
| LMArena Expert | — | 1144 |
Multilingual Not comparable
Magistral Small: —, Qwen1.5-110B: 33.8 (#245)
| Benchmark | Magistral Small | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | — | 1142 |
| LMArena Chinese | — | 1206 |
| LMArena French | — | 1150 |
| LMArena German | — | 1123 |
| LMArena Japanese | — | 1074 |
| LMArena Korean | — | 1044 |
| LMArena Russian | — | 1118 |
| LMArena Spanish | — | 1141 |
Instruction Following Not comparable
Magistral Small: —, Qwen1.5-110B: 60.6 (#247)
| Benchmark | Magistral Small | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | — | 1158 |
Long Context Not comparable
Magistral Small: —, Qwen1.5-110B: 35.0 (#237)
| Benchmark | Magistral Small | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | — | 1157 |
Writing & Preference Not comparable
Magistral Small: —, Qwen1.5-110B: 38.1 (#250)
| Benchmark | Magistral Small | Qwen1.5-110B |
|---|---|---|
| LMArena Text | — | 1175 |
| LMArena Creative Writing | — | 1148 |
| LMArena Multi-Turn | — | 1160 |
Frequently asked questions
Is Magistral Small better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 33.6 to 29.9 on the Noometry Index.
Is Magistral Small or Qwen1.5-110B better for coding?
Magistral Small scores higher on coding benchmarks: 37.8 versus 32.4 in the Noometry coding category.
How many benchmarks do Magistral Small and Qwen1.5-110B share?
0 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and Qwen1.5-110B has 20.