Model comparison
Mistral Medium vs Qwen3 8B
Mistral Medium is the stronger model overall, scoring 36.3 to 33.7 on the Noometry Index. Qwen3 8B costs 9.7× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 8 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 8 benchmarks with published results for both. Mistral Medium scores higher in 3 categories and Qwen3 8B in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 8B leads 36.1 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 56.1% for Qwen3 8B.
- Qwen3 8B is cheaper at $0.18 / $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 | Qwen3 8B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 36.3 | 33.7 |
| Released | 2023-12-11 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 262K | 8K |
| Input $ / M tokens | $1.50 | $0.18 |
| Output $ / M tokens | $7.50 | $0.70 |
| Results tracked | 36 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral Medium: 34.2 (#243), Qwen3 8B: 34.0 (#248)
| Benchmark | Mistral Medium | Qwen3 8B |
|---|---|---|
| SciCode | 40.2% | 22.6% |
| FrontierCode | 8% | — |
| WeirdML | 43.7% | — |
| LMArena Coding | 1434 | — |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Qwen3 8B leads
Mistral Medium: 28.3 (#90), Qwen3 8B: 30.2 (#78)
| Benchmark | Mistral Medium | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | 42.6% |
Reasoning Mistral Medium leads
Mistral Medium: 24.0 (#167), Qwen3 8B: 16.6 (#303)
| Benchmark | Mistral Medium | Qwen3 8B |
|---|---|---|
| CritPt | 0% | 0% |
| DTBench | 75.5% | 59.7% |
| LMCA | 26.1% | 8.8% |
| Kagi LLM Benchmark | 50% | — |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | 1426 | — |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 136.17 |
Math Qwen3 8B leads
Mistral Medium: 28.1 (#245), Qwen3 8B: 34.9 (#191)
| Benchmark | Mistral Medium | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 56.1% |
| ProofBench | 9% | — |
| LMArena Math | 1408 | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3 8B leads
Mistral Medium: 25.0 (#265), Qwen3 8B: 36.1 (#173)
| Benchmark | Mistral Medium | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 59.5% | 56.8% |
| Vectara Hallucination Rate | 22.7% | 4.8% |
| Humanity's Last Exam | 4.5% | — |
| LMArena Expert | 1408 | — |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Qwen3 8B: —
| Benchmark | Mistral Medium | Qwen3 8B |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Not comparable
Mistral Medium: 52.1 (#91), Qwen3 8B: —
| Benchmark | Mistral Medium | Qwen3 8B |
|---|---|---|
| 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 Not comparable
Mistral Medium: 73.7 (#116), Qwen3 8B: —
| Benchmark | Mistral Medium | Qwen3 8B |
|---|---|---|
| LMArena Instruction Following | 1398 | — |
Long Context Mistral Medium leads
Mistral Medium: 42.9 (#114), Qwen3 8B: 37.9 (#210)
| Benchmark | Mistral Medium | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
| LMArena Longer Query | 1406 | — |
Writing & Preference Not comparable
Mistral Medium: 60.0 (#103), Qwen3 8B: —
| Benchmark | Mistral Medium | Qwen3 8B |
|---|---|---|
| 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 Qwen3 8B?
Mistral Medium is the stronger model overall, scoring 36.3 to 33.7 on the Noometry Index. Qwen3 8B costs 9.7× 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 Qwen3 8B?
Qwen3 8B is cheaper. It lists at $0.18 per million input tokens and $0.70 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Qwen3 8B better for coding?
They score almost the same on coding (34.2 vs 34.0); test both on your own repository before choosing.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 131K.
How many benchmarks do Mistral Medium and Qwen3 8B share?
8 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Qwen3 8B has 11.