Model comparison
Mistral Medium vs Qwen3.5-Flash
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 36.3 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Mistral Medium scores higher in 4 categories and Qwen3.5-Flash in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5-Flash leads 43.2 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 84.4% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Qwen3.5-Flash accepts more context: 1M tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Mistral Medium | Qwen3.5-Flash | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 36.3 | 42.5 |
| Released | 2023-12-11 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 262K | 66K |
| Input $ / M tokens | $1.50 | $0.10 |
| Output $ / M tokens | $7.50 | $0.40 |
| Results tracked | 36 | 32 |
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), Qwen3.5-Flash: 34.2 (#242)
| Benchmark | Mistral Medium | Qwen3.5-Flash |
|---|---|---|
| LMArena Coding | 1434 | 1412 |
| ALE-Bench | 763.98 | 221.8 |
| FrontierCode | 8% | — |
| LMArena WebDev | — | 1244 |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.3 (#90), Qwen3.5-Flash: —
| Benchmark | Mistral Medium | Qwen3.5-Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
| Vending-Bench 2 | — | 462.69 |
Reasoning Qwen3.5-Flash leads
Mistral Medium: 24.0 (#167), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | Mistral Medium | Qwen3.5-Flash |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1403 |
| DTBench | 75.5% | 82.9% |
| LMCA | 26.1% | 29.1% |
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 21% |
| Mystery Game Puzzles | — | 20% |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 143.98 |
Math Qwen3.5-Flash leads
Mistral Medium: 28.1 (#245), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | Mistral Medium | Qwen3.5-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 84.4% |
| LMArena Math | 1408 | 1407 |
| FrontierMath (Feb 2025 set) | 0.3% | 6.2% |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| ProofBench | 9% | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3.5-Flash leads
Mistral Medium: 25.0 (#265), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | Mistral Medium | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 59.5% | 82.3% |
| Vectara Hallucination Rate | 22.7% | 10.5% |
| LMArena Expert | 1408 | 1407 |
| Humanity's Last Exam | 4.5% | — |
| SimpleQA Verified | — | 20.3% |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Qwen3.5-Flash: —
| Benchmark | Mistral Medium | Qwen3.5-Flash |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), Qwen3.5-Flash: 50.5 (#121)
| Benchmark | Mistral Medium | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1408 | 1385 |
| LMArena Chinese | 1447 | 1446 |
| LMArena French | 1459 | 1412 |
| LMArena German | 1432 | 1390 |
| LMArena Japanese | 1378 | 1368 |
| LMArena Korean | 1380 | 1344 |
| LMArena Russian | 1411 | 1379 |
| LMArena Spanish | 1433 | 1400 |
Instruction Following Mistral Medium leads
Mistral Medium: 73.7 (#116), Qwen3.5-Flash: 72.6 (#139)
| Benchmark | Mistral Medium | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1398 | 1374 |
Long Context Too close to call
Mistral Medium: 42.9 (#114), Qwen3.5-Flash: 42.4 (#124)
| Benchmark | Mistral Medium | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1406 | 1392 |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Qwen3.5-Flash: 57.9 (#122)
| Benchmark | Mistral Medium | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1424 | 1397 |
| LMArena Creative Writing | 1391 | 1343 |
| LMArena Multi-Turn | 1418 | 1393 |
| Short-Story Creative Writing | 77.3% | — |
Frequently asked questions
Is Mistral Medium better than Qwen3.5-Flash?
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 36.3 on the Noometry Index.
Which is cheaper, Mistral Medium or Qwen3.5-Flash?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Qwen3.5-Flash better for coding?
They score almost the same on coding (34.2 vs 34.2); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.5-Flash does, with 1M tokens against 262K.
How many benchmarks do Mistral Medium and Qwen3.5-Flash share?
24 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Qwen3.5-Flash has 32.