Model comparison
Pixtral Large vs Qwen-14B
Pixtral Large and Qwen-14B score almost the same on the Noometry Index (31.7 vs 30.8), so choose on price, context window or the category you care about most.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- The widest gap is in writing & preference, where Pixtral Large leads 32.9 to 27.8.
Side by side
| Pixtral Large | Qwen-14B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.7 | 30.8 |
| Released | 2024-11-01 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 3 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Pixtral Large: —, Qwen-14B: 30.6 (#283)
| Benchmark | Pixtral Large | Qwen-14B |
|---|---|---|
| LMArena Coding | — | 1072 |
Reasoning Pixtral Large leads
Pixtral Large: 20.9 (#208), Qwen-14B: 18.7 (#255)
| Benchmark | Pixtral Large | Qwen-14B |
|---|---|---|
| EnigmaEval | 0.8% | — |
| LMArena Hard Prompts | — | 1027 |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 112.8 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Not comparable
Pixtral Large: —, Qwen-14B: 28.7 (#224)
| Benchmark | Pixtral Large | Qwen-14B |
|---|---|---|
| LMArena Math | — | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Pixtral Large: —, Qwen-14B: —
| Benchmark | Pixtral Large | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multimodal Not comparable
Pixtral Large: 30.0 (#105), Qwen-14B: —
| Benchmark | Pixtral Large | Qwen-14B |
|---|---|---|
| LMArena Vision | 1089 | — |
Multilingual Not comparable
Pixtral Large: —, Qwen-14B: 27.7 (#270)
| Benchmark | Pixtral Large | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1042 |
| LMArena Chinese | — | 1077 |
Instruction Following Not comparable
Pixtral Large: —, Qwen-14B: 52.6 (#284)
| Benchmark | Pixtral Large | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |
Long Context Not comparable
Pixtral Large: —, Qwen-14B: 31.3 (#276)
| Benchmark | Pixtral Large | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1029 |
Writing & Preference Pixtral Large leads
Pixtral Large: 32.9 (#273), Qwen-14B: 27.8 (#294)
| Benchmark | Pixtral Large | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| EQ-Bench Creative Writing | 988 | — |
| LMArena Multi-Turn | — | 1022 |
Frequently asked questions
Is Pixtral Large better than Qwen-14B?
Pixtral Large and Qwen-14B score almost the same on the Noometry Index (31.7 vs 30.8), so choose on price, context window or the category you care about most.
How many benchmarks do Pixtral Large and Qwen-14B share?
0 benchmarks have published results for both models. Pixtral Large has 3 scored results on Noometry and Qwen-14B has 18.