Model comparison
Mistral Medium vs Qwen2.5 7B Instruct
Mistral Medium is the stronger model overall, scoring 36.3 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 9.8× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Mistral Medium scores higher in 6 categories and Qwen2.5 7B Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Medium leads 28.1 to 12.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 2.5% for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 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 7B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 36.3 | 29.0 |
| Released | 2023-12-11 | 2024-09 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 262K | 8K |
| Input $ / M tokens | $1.50 | $0.17 |
| Output $ / M tokens | $7.50 | $0.70 |
| Results tracked | 36 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
Mistral Medium: 34.2 (#243), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Mistral Medium | Qwen2.5 7B Instruct |
|---|---|---|
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1434 | — |
| BigCodeBench Complete | — | 46.1% |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Mistral Medium leads
Mistral Medium: 28.3 (#90), Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Mistral Medium | Qwen2.5 7B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
| BALROG | — | 7.8% |
Reasoning Mistral Medium leads
Mistral Medium: 24.0 (#167), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Mistral Medium | Qwen2.5 7B Instruct |
|---|---|---|
| DTBench | 75.5% | 47.7% |
| LMCA | 26.1% | 6.4% |
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1426 | — |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 118.51 |
Math Mistral Medium leads
Mistral Medium: 28.1 (#245), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Mistral Medium | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 2.5% |
| ProofBench | 9% | — |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1408 | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Mistral Medium leads
Mistral Medium: 25.0 (#265), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Mistral Medium | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 59.5% | 35.5% |
| Humanity's Last Exam | 4.5% | — |
| MMLU-Pro | — | 53.9% |
| Vectara Hallucination Rate | 22.7% | — |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1408 | — |
| MMLU | — | 72.9% |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Qwen2.5 7B Instruct: —
| Benchmark | Mistral Medium | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Not comparable
Mistral Medium: 52.1 (#91), Qwen2.5 7B Instruct: —
| Benchmark | Mistral Medium | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1408 | — |
| LMArena Chinese | 1447 | — |
| LMArena French | 1459 | — |
| LMArena German | 1432 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1380 | — |
| LMArena Russian | 1411 | — |
| LMArena Spanish | 1433 | — |
Instruction Following Mistral Medium leads
Mistral Medium: 73.7 (#116), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Mistral Medium | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1398 | — |
Long Context Not comparable
Mistral Medium: 42.9 (#114), Qwen2.5 7B Instruct: —
| Benchmark | Mistral Medium | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1406 | — |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Mistral Medium | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1424 | — |
| LMArena Creative Writing | 1391 | — |
| Short-Story Creative Writing | 77.3% | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1418 | — |
Frequently asked questions
Is Mistral Medium better than Qwen2.5 7B Instruct?
Mistral Medium is the stronger model overall, scoring 36.3 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 9.8× 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 7B Instruct?
Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Qwen2.5 7B Instruct better for coding?
Qwen2.5 7B Instruct scores higher on coding benchmarks: 36.5 versus 34.2 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 7B Instruct share?
4 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Qwen2.5 7B Instruct has 15.