Model comparison
Mistral Large 3 vs Qwen2.5-Coder-32B
Mistral Large 3 is the stronger model overall, scoring 39.1 to 33.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Mistral Large 3 scores higher in 7 categories and Qwen2.5-Coder-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 3 leads 60.0 to 41.6.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- Mistral Large 3 accepts more context: 262K tokens versus 33K.
Side by side
| Mistral Large 3 | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 39.1 | 33.4 |
| Released | 2025-12-02 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 262K | 33K |
| Max output | 8K | 29K |
| Input $ / M tokens | $0.25 | $0.66 |
| Output $ / M tokens | $0.75 | $1 |
| Results tracked | 24 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
Mistral Large 3: 34.4 (#237), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Mistral Large 3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1448 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LMArena WebDev | 1230 | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Reasoning Qwen2.5-Coder-32B leads
Mistral Large 3: 15.2 (#319), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Mistral Large 3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1429 | 1251 |
| Kagi LLM Benchmark | 50.9% | — |
| NYT Connections (extended) | 7.5% | — |
| Thematic Generalization | 23% | — |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.49 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math Mistral Large 3 leads
Mistral Large 3: 38.7 (#129), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Mistral Large 3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1414 | 1251 |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |
Knowledge Mistral Large 3 leads
Mistral Large 3: 36.0 (#177), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Mistral Large 3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1421 | 1221 |
| Vectara Hallucination Rate | 14.5% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multimodal Not comparable
Mistral Large 3: 38.2 (#66), Qwen2.5-Coder-32B: —
| Benchmark | Mistral Large 3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 1221 | — |
Multilingual Mistral Large 3 leads
Mistral Large 3: 52.5 (#84), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Mistral Large 3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1413 | 1205 |
| LMArena Chinese | 1447 | 1222 |
| LMArena Russian | 1411 | 1228 |
| LMArena French | 1455 | — |
| LMArena German | 1437 | — |
| LMArena Japanese | 1394 | — |
| LMArena Korean | 1384 | — |
| LMArena Spanish | 1440 | — |
Instruction Following Mistral Large 3 leads
Mistral Large 3: 74.0 (#108), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Mistral Large 3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1403 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context Mistral Large 3 leads
Mistral Large 3: 43.1 (#105), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Mistral Large 3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1413 | 1251 |
Writing & Preference Mistral Large 3 leads
Mistral Large 3: 60.0 (#101), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Mistral Large 3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1428 | 1230 |
| LMArena Creative Writing | 1386 | 1174 |
| LMArena Multi-Turn | 1429 | 1222 |
| EQ-Bench Creative Writing | 1412 | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Mistral Large 3 better than Qwen2.5-Coder-32B?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 33.4 on the Noometry Index.
Which is cheaper, Mistral Large 3 or Qwen2.5-Coder-32B?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.
Is Mistral Large 3 or Qwen2.5-Coder-32B better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 33K.
How many benchmarks do Mistral Large 3 and Qwen2.5-Coder-32B share?
12 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Qwen2.5-Coder-32B has 31.