Model comparison
Mistral Small vs Qwen2.5-VL 72B Instruct
Mistral Small is the stronger model overall, scoring 33.1 to 29.4 on the Noometry Index.
Last verified . 2 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. Mistral Small scores higher in 2 categories and Qwen2.5-VL 72B Instruct in 1 category; one gap is clear of the uncertainty.
- The widest gap is in agentic & tool use, where Mistral Small leads 27.9 to 18.4.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- Mistral Small accepts more context: 256K tokens versus 131K.
Side by side
| Mistral Small | Qwen2.5-VL 72B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.1 | 29.4 |
| Released | 2024-02-26 | 2024-09 |
| Weights | Open | Open |
| Context window | 256K | 131K |
| Max output | 256K | 8K |
| Input $ / M tokens | $0.15 | $2.80 |
| Output $ / M tokens | $0.60 | $8.40 |
| Results tracked | 39 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Small: 33.5 (#242), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mistral Small | Qwen2.5-VL 72B Instruct |
|---|---|---|
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| LMArena Coding | 1363 | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Mistral Small leads
Mistral Small: 27.9 (#87), Qwen2.5-VL 72B Instruct: 18.4 (#136)
| Benchmark | Mistral Small | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
| OSWorld | — | 5% |
Reasoning Too close to call
Mistral Small: 19.3 (#238), Qwen2.5-VL 72B Instruct: 20.0 (#228)
| Benchmark | Mistral Small | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 36% |
| CritPt | 0% | — |
| LiveBench Reasoning | 44.8% | — |
| LMArena Hard Prompts | 1336 | — |
| DTBench | 70.9% | — |
| LiveBench Data Analysis | 53.7% | — |
| LMCA | 20.6% | — |
| LiveBench | 44% | — |
Math Not comparable
Mistral Small: 15.4 (#287), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mistral Small | Qwen2.5-VL 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| LiveBench Math | 39.9% | — |
| LMArena Math | 1341 | — |
| MATH Level 5 | 46.8% | — |
Knowledge Not comparable
Mistral Small: 30.9 (#214), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mistral Small | Qwen2.5-VL 72B Instruct |
|---|---|---|
| GPQA Diamond | 47.5% | — |
| Vectara Hallucination Rate | 5.1% | — |
| LMArena Expert | 1293 | — |
| MMLU | 68.7% | — |
Multimodal Too close to call
Mistral Small: 32.9 (#91), Qwen2.5-VL 72B Instruct: 32.9 (#92)
| Benchmark | Mistral Small | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | 1142 | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |
Multilingual Not comparable
Mistral Small: 45.7 (#164), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mistral Small | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Non-English | 1315 | — |
| LMArena Chinese | 1342 | — |
| LMArena French | 1337 | — |
| LMArena German | 1341 | — |
| LMArena Japanese | 1275 | — |
| LMArena Korean | 1260 | — |
| LMArena Russian | 1324 | — |
| LMArena Spanish | 1346 | — |
Instruction Following Not comparable
Mistral Small: 66.6 (#204), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mistral Small | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LiveBench Instruction Following | 63.7% | — |
| LMArena Instruction Following | 1310 | — |
Long Context Not comparable
Mistral Small: 40.4 (#151), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mistral Small | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1327 | — |
Writing & Preference Not comparable
Mistral Small: 52.6 (#165), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mistral Small | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Text | 1338 | — |
| LMArena Creative Writing | 1304 | — |
| LMArena Multi-Turn | 1344 | — |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Qwen2.5-VL 72B Instruct?
Mistral Small is the stronger model overall, scoring 33.1 to 29.4 on the Noometry Index.
Which is cheaper, Mistral Small or Qwen2.5-VL 72B Instruct?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.
Which has the bigger context window?
Mistral Small does, with 256K tokens against 131K.
How many benchmarks do Mistral Small and Qwen2.5-VL 72B Instruct share?
2 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.