Model comparison
Pixtral Large vs Qwen2.5 72B Instruct
Pixtral Large and Qwen2.5 72B Instruct score almost the same on the Noometry Index (32.2 vs 31.9), 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 Qwen2.5 72B Instruct leads 46.7 to 32.9.
- Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $2 / $6 for Pixtral Large.
- Qwen2.5 72B Instruct accepts more context: 131K tokens versus 128K.
Side by side
| Pixtral Large | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 32.2 | 31.9 |
| Released | 2024-11-01 | 2024-09 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 128K | 8K |
| Input $ / M tokens | $2 | $1.40 |
| Output $ / M tokens | $6 | $5.60 |
| Results tracked | 3 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Pixtral Large: —, Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Pixtral Large | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| LMArena Coding | — | 1292 |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Pixtral Large: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Pixtral Large | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Too close to call
Pixtral Large: 21.7 (#218), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Pixtral Large | Qwen2.5 72B Instruct |
|---|---|---|
| EnigmaEval | 0.8% | — |
| LMArena Hard Prompts | — | 1271 |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Not comparable
Pixtral Large: —, Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Pixtral Large | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| LMArena Math | — | 1283 |
| MATH Level 5 | — | 63.2% |
Knowledge Not comparable
Pixtral Large: —, Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Pixtral Large | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multimodal Not comparable
Pixtral Large: 30.6 (#111), Qwen2.5 72B Instruct: —
| Benchmark | Pixtral Large | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1089 | — |
Multilingual Not comparable
Pixtral Large: —, Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Pixtral Large | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | — | 1252 |
| LMArena Chinese | — | 1272 |
| LMArena French | — | 1280 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1256 |
Instruction Following Not comparable
Pixtral Large: —, Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Pixtral Large | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | — | 80.6% |
| LMArena Instruction Following | — | 1254 |
Long Context Not comparable
Pixtral Large: —, Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Pixtral Large | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | — | 1282 |
Writing & Preference Qwen2.5 72B Instruct leads
Pixtral Large: 32.9 (#278), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Pixtral Large | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | — | 1269 |
| LMArena Creative Writing | — | 1221 |
| EQ-Bench Creative Writing | 988 | — |
| WildBench | — | 80.2% |
| LMArena Multi-Turn | — | 1272 |
Frequently asked questions
Is Pixtral Large better than Qwen2.5 72B Instruct?
Pixtral Large and Qwen2.5 72B Instruct score almost the same on the Noometry Index (32.2 vs 31.9), so choose on price, context window or the category you care about most.
Which is cheaper, Pixtral Large or Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; Pixtral Large lists at $2 and $6.
Which has the bigger context window?
Qwen2.5 72B Instruct does, with 131K tokens against 128K.
How many benchmarks do Pixtral Large and Qwen2.5 72B Instruct share?
0 benchmarks have published results for both models. Pixtral Large has 3 scored results on Noometry and Qwen2.5 72B Instruct has 43.