Model comparison
Pixtral Large vs Qwen1.5-72B
Pixtral Large is the stronger model overall, scoring 31.7 to 30.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- The widest gap is in writing & preference, where Qwen1.5-72B leads 37.4 to 32.9.
Side by side
| Pixtral Large | Qwen1.5-72B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.7 | 30.3 |
| Released | 2024-11-01 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 3 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Pixtral Large: —, Qwen1.5-72B: 31.4 (#272)
| Benchmark | Pixtral Large | Qwen1.5-72B |
|---|---|---|
| BigCodeBench Instruct | — | 33.2% |
| LMArena Coding | — | 1166 |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Reasoning Too close to call
Pixtral Large: 20.9 (#208), Qwen1.5-72B: 21.2 (#201)
| Benchmark | Pixtral Large | Qwen1.5-72B |
|---|---|---|
| EnigmaEval | 0.8% | — |
| LMArena Hard Prompts | — | 1148 |
Math Not comparable
Pixtral Large: —, Qwen1.5-72B: 30.7 (#205)
| Benchmark | Pixtral Large | Qwen1.5-72B |
|---|---|---|
| LMArena Math | — | 1164 |
Knowledge Not comparable
Pixtral Large: —, Qwen1.5-72B: 11.5 (#295)
| Benchmark | Pixtral Large | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | — | 28.8% |
| LMArena Expert | — | 1136 |
Multimodal Not comparable
Pixtral Large: 30.0 (#105), Qwen1.5-72B: —
| Benchmark | Pixtral Large | Qwen1.5-72B |
|---|---|---|
| LMArena Vision | 1089 | — |
Multilingual Not comparable
Pixtral Large: —, Qwen1.5-72B: 33.4 (#248)
| Benchmark | Pixtral Large | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | — | 1135 |
| LMArena Chinese | — | 1186 |
| LMArena French | — | 1158 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1049 |
| LMArena Russian | — | 1104 |
| LMArena Spanish | — | 1110 |
Instruction Following Not comparable
Pixtral Large: —, Qwen1.5-72B: 59.6 (#251)
| Benchmark | Pixtral Large | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | — | 1142 |
Long Context Not comparable
Pixtral Large: —, Qwen1.5-72B: 35.0 (#238)
| Benchmark | Pixtral Large | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | — | 1157 |
Writing & Preference Qwen1.5-72B leads
Pixtral Large: 32.9 (#273), Qwen1.5-72B: 37.4 (#253)
| Benchmark | Pixtral Large | Qwen1.5-72B |
|---|---|---|
| LMArena Text | — | 1166 |
| LMArena Creative Writing | — | 1137 |
| EQ-Bench Creative Writing | 988 | — |
| LMArena Multi-Turn | — | 1160 |
Frequently asked questions
Is Pixtral Large better than Qwen1.5-72B?
Pixtral Large is the stronger model overall, scoring 31.7 to 30.3 on the Noometry Index.
How many benchmarks do Pixtral Large and Qwen1.5-72B share?
0 benchmarks have published results for both models. Pixtral Large has 3 scored results on Noometry and Qwen1.5-72B has 22.