Model comparison
Mistral Small 3.1 vs Qwen2.5 72B Instruct
Mistral Small 3.1 and Qwen2.5 72B Instruct score almost the same on the Noometry Index (31.7 vs 31.9), so choose on price, context window or the category you care about most.
Last verified . 25 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Mistral Small 3.1 scores higher in 3 categories and Qwen2.5 72B Instruct in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 72B Instruct leads 46.7 to 37.0.
- The biggest single-benchmark swing is Omni-MATH: 24.8% for Mistral Small 3.1 and 33% for Qwen2.5 72B Instruct.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct accepts more context: 131K tokens versus 128K.
Side by side
| Mistral Small 3.1 | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.7 | 31.9 |
| Released | 2025-03-17 | 2024-09 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 102K | 8K |
| Input $ / M tokens | $0.35 | $1.40 |
| Output $ / M tokens | $0.56 | $5.60 |
| Results tracked | 28 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Mistral Small 3.1: 38.3 (#179), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Mistral Small 3.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1309 | 1292 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Mistral Small 3.1: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Mistral Small 3.1 | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
Mistral Small 3.1: 19.7 (#254), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Mistral Small 3.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1278 | 1271 |
| Epoch Capabilities Index | 127.48 | 129 |
| Chess Puzzles | 1% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Qwen2.5 72B Instruct leads
Mistral Small 3.1: 14.7 (#301), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Mistral Small 3.1 | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.9% | 8.1% |
| Omni-MATH | 24.8% | 33% |
| LMArena Math | 1262 | 1283 |
| MATH Level 5 | — | 63.2% |
Knowledge Qwen2.5 72B Instruct leads
Mistral Small 3.1: 22.6 (#271), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Mistral Small 3.1 | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 41.9% | 49.1% |
| MMLU-Pro | 61% | 63.1% |
| GPQA (HELM) | 39.2% | 42.6% |
| LMArena Expert | 1257 | 1245 |
| Confabulations | — | 19.1% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multimodal Not comparable
Mistral Small 3.1: 33.2 (#99), Qwen2.5 72B Instruct: —
| Benchmark | Mistral Small 3.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1136 | — |
Multilingual Too close to call
Mistral Small 3.1: 41.2 (#209), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Mistral Small 3.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1255 | 1252 |
| LMArena Chinese | 1253 | 1272 |
| LMArena French | 1273 | 1280 |
| LMArena German | 1266 | 1234 |
| LMArena Japanese | 1208 | 1180 |
| LMArena Korean | 1206 | 1188 |
| LMArena Russian | 1263 | 1264 |
| LMArena Spanish | 1283 | 1256 |
Instruction Following Qwen2.5 72B Instruct leads
Mistral Small 3.1: 63.6 (#230), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Mistral Small 3.1 | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | 75% | 80.6% |
| LMArena Instruction Following | 1264 | 1254 |
Long Context Too close to call
Mistral Small 3.1: 39.5 (#178), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Mistral Small 3.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1299 | 1282 |
Writing & Preference Qwen2.5 72B Instruct leads
Mistral Small 3.1: 37.0 (#259), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Mistral Small 3.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1277 | 1269 |
| LMArena Creative Writing | 1253 | 1221 |
| WildBench | 78.8% | 80.2% |
| LMArena Multi-Turn | 1270 | 1272 |
| EQ-Bench Creative Writing | 761 | — |
Frequently asked questions
Is Mistral Small 3.1 better than Qwen2.5 72B Instruct?
Mistral Small 3.1 and Qwen2.5 72B Instruct score almost the same on the Noometry Index (31.7 vs 31.9), so choose on price, context window or the category you care about most.
Which is cheaper, Mistral Small 3.1 or Qwen2.5 72B Instruct?
Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Mistral Small 3.1 or Qwen2.5 72B Instruct better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Qwen2.5 72B Instruct does, with 131K tokens against 128K.
How many benchmarks do Mistral Small 3.1 and Qwen2.5 72B Instruct share?
25 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and Qwen2.5 72B Instruct has 43.