Model comparison
Mistral Medium vs Qwen2.5 32B Instruct
Mistral Medium is the stronger model overall, scoring 36.0 to 29.7 on the Noometry Index. Qwen2.5 32B Instruct costs 2.4× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Mistral Medium scores higher in 2 categories and Qwen2.5 32B Instruct in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Medium leads 27.2 to 15.3.
- The biggest single-benchmark swing is MATH Level 5: 81.6% for Mistral Medium and 56.1% for Qwen2.5 32B Instruct.
- Qwen2.5 32B Instruct is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 131K.
Side by side
| Mistral Medium | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 36.0 | 29.7 |
| Released | 2023-12-11 | 2024-09 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 262K | 8K |
| Input $ / M tokens | $1.50 | $0.70 |
| Output $ / M tokens | $7.50 | $2.80 |
| Results tracked | 36 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 32B Instruct leads
Mistral Medium: 33.8 (#241), Qwen2.5 32B Instruct: 38.1 (#165)
| Benchmark | Mistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| BigCodeBench Instruct | — | 45% |
| LMArena Coding | 1434 | — |
| BigCodeBench Complete | — | 52.3% |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.1 (#84), Qwen2.5 32B Instruct: —
| Benchmark | Mistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Mistral Medium leads
Mistral Medium: 23.3 (#165), Qwen2.5 32B Instruct: 18.5 (#262)
| Benchmark | Mistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1426 | — |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 128.52 |
Math Mistral Medium leads
Mistral Medium: 27.2 (#238), Qwen2.5 32B Instruct: 15.3 (#289)
| Benchmark | Mistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 7.4% |
| MATH Level 5 | 81.6% | 56.1% |
| ProofBench | 9% | — |
| LMArena Math | 1409 | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Too close to call
Mistral Medium: 24.9 (#260), Qwen2.5 32B Instruct: 24.9 (#259)
| Benchmark | Mistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | 59.5% | 46.1% |
| Humanity's Last Exam | 4.5% | — |
| Vectara Hallucination Rate | 22.7% | — |
| LMArena Expert | 1408 | — |
Multimodal Not comparable
Mistral Medium: 34.6 (#82), Qwen2.5 32B Instruct: —
| Benchmark | Mistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Not comparable
Mistral Medium: 52.3 (#86), Qwen2.5 32B Instruct: —
| Benchmark | Mistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Non-English | 1408 | — |
| LMArena Chinese | 1448 | — |
| LMArena French | 1460 | — |
| LMArena German | 1433 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1382 | — |
| LMArena Russian | 1411 | — |
| LMArena Spanish | 1433 | — |
Instruction Following Not comparable
Mistral Medium: 73.9 (#111), Qwen2.5 32B Instruct: —
| Benchmark | Mistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Instruction Following | 1398 | — |
Long Context Not comparable
Mistral Medium: 42.9 (#108), Qwen2.5 32B Instruct: —
| Benchmark | Mistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Longer Query | 1406 | — |
Writing & Preference Not comparable
Mistral Medium: 60.2 (#97), Qwen2.5 32B Instruct: —
| Benchmark | Mistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Text | 1424 | — |
| LMArena Creative Writing | 1391 | — |
| Short-Story Creative Writing | 77.3% | — |
| LMArena Multi-Turn | 1418 | — |
Frequently asked questions
Is Mistral Medium better than Qwen2.5 32B Instruct?
Mistral Medium is the stronger model overall, scoring 36.0 to 29.7 on the Noometry Index. Qwen2.5 32B Instruct costs 2.4× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Which is cheaper, Mistral Medium or Qwen2.5 32B Instruct?
Qwen2.5 32B Instruct is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Qwen2.5 32B Instruct better for coding?
Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.1 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 131K.
How many benchmarks do Mistral Medium and Qwen2.5 32B Instruct share?
3 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Qwen2.5 32B Instruct has 7.