Model comparison
Mistral Large vs Qwen2.5-Coder-32B
Qwen2.5-Coder-32B is the stronger model overall, scoring 32.9 to 31.6 on the Noometry Index.
Last verified . 25 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Mistral Large scores higher in 4 categories and Qwen2.5-Coder-32B in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Coder-32B leads 30.8 to 17.1.
- The biggest single-benchmark swing is BigCodeBench Complete: 38.3% for Mistral Large and 58% for Qwen2.5-Coder-32B.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $2 / $6 for Mistral Large.
- Mistral Large accepts more context: 131K tokens versus 33K.
Side by side
| Mistral Large | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.6 | 32.9 |
| Released | 2024-02-26 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 131K | 33K |
| Max output | 16K | 29K |
| Input $ / M tokens | $2 | $0.66 |
| Output $ / M tokens | $6 | $1 |
| Results tracked | 51 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Mistral Large: 33.8 (#240), Qwen2.5-Coder-32B: 22.4 (#328)
| Benchmark | Mistral Large | Qwen2.5-Coder-32B |
|---|---|---|
| BigCodeBench Instruct | 30% | 49% |
| LiveBench Coding | 47.1% | 56.9% |
| LMArena Coding | 1277 | 1276 |
| BigCodeBench Complete | 38.3% | 58% |
| HumanEval+ | 62.2% | 87.2% |
| MBPP+ | 59.5% | 77% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| SciCode | 36.2% | — |
| ALE-Bench | 264.7 | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.4 (#83), Qwen2.5-Coder-32B: —
| Benchmark | Mistral Large | Qwen2.5-Coder-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Qwen2.5-Coder-32B leads
Mistral Large: 15.4 (#305), Qwen2.5-Coder-32B: 20.4 (#220)
| Benchmark | Mistral Large | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Reasoning | 43.5% | 42.1% |
| LMArena Hard Prompts | 1257 | 1251 |
| LiveBench Data Analysis | 50.1% | 49.9% |
| Epoch Capabilities Index | 128.52 | 119.41 |
| LiveBench | 48.4% | 46.2% |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| DTBench | 65.1% | — |
| LMCA | 16.7% | — |
| ForecastBench | 57.1 | — |
| HellaSwag | — | 83% |
| WinoGrande | — | 80.8% |
Math Qwen2.5-Coder-32B leads
Mistral Large: 17.1 (#285), Qwen2.5-Coder-32B: 30.8 (#203)
| Benchmark | Mistral Large | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Math | 42.5% | 46.6% |
| LMArena Math | 1262 | 1251 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 28.1% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
| GSM8K | — | 93% |
Knowledge Qwen2.5-Coder-32B leads
Mistral Large: 30.0 (#224), Qwen2.5-Coder-32B: 32.9 (#200)
| Benchmark | Mistral Large | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1232 | 1221 |
| MMLU | 80% | 79.1% |
| GPQA Diamond | 51.3% | — |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| ARC (AI2) Challenge | — | 70.5% |
Multilingual Mistral Large leads
Mistral Large: 40.1 (#214), Qwen2.5-Coder-32B: 38.0 (#230)
| Benchmark | Mistral Large | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1237 | 1205 |
| LMArena Chinese | 1240 | 1222 |
| LMArena Russian | 1257 | 1228 |
| LMArena French | 1324 | — |
| LMArena German | 1254 | — |
| LMArena Japanese | 1187 | — |
| LMArena Korean | 1202 | — |
| LMArena Spanish | 1268 | — |
Instruction Following Mistral Large leads
Mistral Large: 68.1 (#186), Qwen2.5-Coder-32B: 61.6 (#240)
| Benchmark | Mistral Large | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Instruction Following | 67.9% | 58.7% |
| LMArena Instruction Following | 1249 | 1223 |
| IFEval | 87.7% | — |
Long Context Too close to call
Mistral Large: 38.3 (#194), Qwen2.5-Coder-32B: 37.9 (#204)
| Benchmark | Mistral Large | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1262 | 1251 |
Writing & Preference Too close to call
Mistral Large: 40.9 (#237), Qwen2.5-Coder-32B: 41.8 (#235)
| Benchmark | Mistral Large | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1266 | 1230 |
| LMArena Creative Writing | 1243 | 1174 |
| LMArena Multi-Turn | 1260 | 1222 |
| LiveBench Language | 39.4% | 23.3% |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
Frequently asked questions
Is Mistral Large better than Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is the stronger model overall, scoring 32.9 to 31.6 on the Noometry Index.
Which is cheaper, Mistral Large or Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Qwen2.5-Coder-32B better for coding?
Mistral Large scores higher on coding benchmarks: 33.8 versus 22.4 in the Noometry coding category.
Which has the bigger context window?
Mistral Large does, with 131K tokens against 33K.
How many benchmarks do Mistral Large and Qwen2.5-Coder-32B share?
25 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen2.5-Coder-32B has 31.