Model comparison
Mistral Small vs Qwen2.5-Coder-32B
Mistral Small and Qwen2.5-Coder-32B score almost the same on the Noometry Index (33.4 vs 33.4), so choose on price, context window or the category you care about most.
Last verified . 22 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Mistral Small scores higher in 5 categories and Qwen2.5-Coder-32B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Coder-32B leads 33.3 to 16.4.
- The biggest single-benchmark swing is LiveBench Coding: 36.2% for Mistral Small and 56.9% for Qwen2.5-Coder-32B.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- Mistral Small accepts more context: 262K tokens versus 33K.
Side by side
| Mistral Small | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 33.4 |
| Released | 2024-02-26 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 262K | 33K |
| Max output | 256K | 29K |
| Input $ / M tokens | $0.15 | $0.66 |
| Output $ / M tokens | $0.60 | $1 |
| Results tracked | 39 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Mistral Small: 34.0 (#247), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Mistral Small | Qwen2.5-Coder-32B |
|---|---|---|
| BigCodeBench Instruct | 36.1% | 49% |
| LiveBench Coding | 36.2% | 56.9% |
| LMArena Coding | 1362 | 1276 |
| BigCodeBench Complete | 46.6% | 58% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| SciCode | 26.5% | — |
| ALE-Bench | 497.62 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
Mistral Small: 28.1 (#93), Qwen2.5-Coder-32B: —
| Benchmark | Mistral Small | Qwen2.5-Coder-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
Reasoning Qwen2.5-Coder-32B leads
Mistral Small: 19.8 (#250), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Mistral Small | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Reasoning | 44.8% | 42.1% |
| LMArena Hard Prompts | 1335 | 1251 |
| LiveBench Data Analysis | 53.7% | 49.9% |
| LiveBench | 44% | 46.2% |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| DTBench | 70.9% | — |
| LMCA | 20.6% | — |
| Epoch Capabilities Index | — | 119.49 |
| HellaSwag | — | 83% |
| WinoGrande | — | 80.8% |
Math Qwen2.5-Coder-32B leads
Mistral Small: 16.4 (#293), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Mistral Small | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Math | 39.9% | 46.6% |
| LMArena Math | 1341 | 1251 |
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| MATH Level 5 | 46.8% | — |
| GSM8K | — | 93% |
Knowledge Qwen2.5-Coder-32B leads
Mistral Small: 31.0 (#222), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Mistral Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1291 | 1221 |
| MMLU | 68.7% | 79.1% |
| GPQA Diamond | 47.5% | — |
| Vectara Hallucination Rate | 5.1% | — |
| ARC (AI2) Challenge | — | 70.5% |
Multimodal Not comparable
Mistral Small: 33.5 (#96), Qwen2.5-Coder-32B: —
| Benchmark | Mistral Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Mistral Small leads
Mistral Small: 45.5 (#169), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Mistral Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1315 | 1205 |
| LMArena Chinese | 1340 | 1222 |
| LMArena Russian | 1324 | 1228 |
| LMArena French | 1337 | — |
| LMArena German | 1340 | — |
| LMArena Japanese | 1275 | — |
| LMArena Korean | 1259 | — |
| LMArena Spanish | 1346 | — |
Instruction Following Mistral Small leads
Mistral Small: 66.4 (#209), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Mistral Small | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Instruction Following | 63.7% | 58.7% |
| LMArena Instruction Following | 1310 | 1223 |
Long Context Mistral Small leads
Mistral Small: 40.4 (#156), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Mistral Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1327 | 1251 |
Writing & Preference Mistral Small leads
Mistral Small: 52.5 (#171), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Mistral Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1338 | 1230 |
| LMArena Creative Writing | 1305 | 1174 |
| LMArena Multi-Turn | 1344 | 1222 |
| LiveBench Language | 30.5% | 23.3% |
Frequently asked questions
Is Mistral Small better than Qwen2.5-Coder-32B?
Mistral Small and Qwen2.5-Coder-32B score almost the same on the Noometry Index (33.4 vs 33.4), so choose on price, context window or the category you care about most.
Which is cheaper, Mistral Small or Qwen2.5-Coder-32B?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.
Is Mistral Small or Qwen2.5-Coder-32B better for coding?
Mistral Small scores higher on coding benchmarks: 34.0 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 262K tokens against 33K.
How many benchmarks do Mistral Small and Qwen2.5-Coder-32B share?
22 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen2.5-Coder-32B has 31.