Model comparison
Ministral 8B vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 28.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Ministral 8B scores higher in 5 categories and Qwen1.5-110B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5-110B leads 31.2 to 12.6.
Side by side
| Ministral 8B | Qwen1.5-110B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 28.2 | 34.2 |
| Released | 2024-10-01 | 2024-04-25 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 17 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Ministral 8B: 35.0 (#230), Qwen1.5-110B: 33.0 (#264)
| Benchmark | Ministral 8B | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1202 | 1184 |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
Agentic & Tool Use Not comparable
Ministral 8B: 16.4 (#148), Qwen1.5-110B: —
| Benchmark | Ministral 8B | Qwen1.5-110B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
Reasoning Qwen1.5-110B leads
Ministral 8B: 18.4 (#281), Qwen1.5-110B: 22.7 (#189)
| Benchmark | Ministral 8B | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1168 |
| DTBench | 45.7% | — |
| ForecastBench | — | 57.7 |
Math Qwen1.5-110B leads
Ministral 8B: 25.7 (#267), Qwen1.5-110B: 33.7 (#201)
| Benchmark | Ministral 8B | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1188 | 1185 |
| MATH Level 5 | 14.9% | — |
Knowledge Qwen1.5-110B leads
Ministral 8B: 12.6 (#297), Qwen1.5-110B: 31.2 (#219)
| Benchmark | Ministral 8B | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1170 | 1144 |
| GPQA Diamond | 27.1% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multilingual Ministral 8B leads
Ministral 8B: 35.1 (#247), Qwen1.5-110B: 33.6 (#250)
| Benchmark | Ministral 8B | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1165 | 1142 |
| LMArena Chinese | 1193 | 1206 |
| LMArena Russian | 1195 | 1118 |
| LMArena French | — | 1151 |
| LMArena German | — | 1123 |
| LMArena Japanese | — | 1074 |
| LMArena Korean | — | 1044 |
| LMArena Spanish | — | 1142 |
Instruction Following Too close to call
Ministral 8B: 60.5 (#250), Qwen1.5-110B: 60.3 (#252)
| Benchmark | Ministral 8B | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1161 | 1158 |
Long Context Ministral 8B leads
Ministral 8B: 36.7 (#227), Qwen1.5-110B: 35.1 (#242)
| Benchmark | Ministral 8B | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1212 | 1157 |
Writing & Preference Ministral 8B leads
Ministral 8B: 39.6 (#246), Qwen1.5-110B: 38.0 (#255)
| Benchmark | Ministral 8B | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1191 | 1175 |
| LMArena Creative Writing | 1175 | 1148 |
| LMArena Multi-Turn | 1166 | 1160 |
Frequently asked questions
Is Ministral 8B better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 28.2 on the Noometry Index.
Is Ministral 8B or Qwen1.5-110B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 33.0 in the Noometry coding category.
How many benchmarks do Ministral 8B and Qwen1.5-110B share?
12 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Qwen1.5-110B has 20.