Model comparison
Mistral Small vs Qwen3.5-Flash
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 33.4 on the Noometry Index.
Last verified . 23 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Mistral Small scores higher in 0 categories and Qwen3.5-Flash in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5-Flash leads 37.4 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 5.8% for Mistral Small and 84.4% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- Qwen3.5-Flash accepts more context: 1M tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Mistral Small | Qwen3.5-Flash | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 42.5 |
| Released | 2024-02-26 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 256K | 66K |
| Input $ / M tokens | $0.15 | $0.10 |
| Output $ / M tokens | $0.60 | $0.40 |
| Results tracked | 39 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral Small: 34.0 (#247), Qwen3.5-Flash: 34.2 (#242)
| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Coding | 1362 | 1412 |
| ALE-Bench | 497.62 | 221.8 |
| LMArena WebDev | — | 1244 |
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
Agentic & Tool Use Not comparable
Mistral Small: 28.1 (#93), Qwen3.5-Flash: —
| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
| Vending-Bench 2 | — | 462.69 |
Reasoning Qwen3.5-Flash leads
Mistral Small: 19.8 (#250), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Hard Prompts | 1335 | 1403 |
| DTBench | 70.9% | 82.9% |
| LMCA | 20.6% | 29.1% |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 21% |
| LiveBench Reasoning | 44.8% | — |
| Mystery Game Puzzles | — | 20% |
| LiveBench Data Analysis | 53.7% | — |
| Epoch Capabilities Index | — | 143.98 |
| LiveBench | 44% | — |
Math Qwen3.5-Flash leads
Mistral Small: 16.4 (#293), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 84.4% |
| LMArena Math | 1341 | 1407 |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| LiveBench Math | 39.9% | — |
| MATH Level 5 | 46.8% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3.5-Flash leads
Mistral Small: 31.0 (#222), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 47.5% | 82.3% |
| Vectara Hallucination Rate | 5.1% | 10.5% |
| LMArena Expert | 1291 | 1407 |
| SimpleQA Verified | — | 20.3% |
| MMLU | 68.7% | — |
Multimodal Not comparable
Mistral Small: 33.5 (#96), Qwen3.5-Flash: —
| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Qwen3.5-Flash leads
Mistral Small: 45.5 (#169), Qwen3.5-Flash: 50.5 (#121)
| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1315 | 1385 |
| LMArena Chinese | 1340 | 1446 |
| LMArena French | 1337 | 1412 |
| LMArena German | 1340 | 1390 |
| LMArena Japanese | 1275 | 1368 |
| LMArena Korean | 1259 | 1344 |
| LMArena Russian | 1324 | 1379 |
| LMArena Spanish | 1346 | 1400 |
Instruction Following Qwen3.5-Flash leads
Mistral Small: 66.4 (#209), Qwen3.5-Flash: 72.6 (#139)
| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1310 | 1374 |
| LiveBench Instruction Following | 63.7% | — |
Long Context Qwen3.5-Flash leads
Mistral Small: 40.4 (#156), Qwen3.5-Flash: 42.4 (#124)
| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1327 | 1392 |
Writing & Preference Qwen3.5-Flash leads
Mistral Small: 52.5 (#171), Qwen3.5-Flash: 57.9 (#122)
| Benchmark | Mistral Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1338 | 1397 |
| LMArena Creative Writing | 1305 | 1343 |
| LMArena Multi-Turn | 1344 | 1393 |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Qwen3.5-Flash?
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 33.4 on the Noometry Index.
Which is cheaper, Mistral Small 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 Small lists at $0.15 and $0.60.
Is Mistral Small or Qwen3.5-Flash better for coding?
They score almost the same on coding (34.0 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 Small and Qwen3.5-Flash share?
23 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen3.5-Flash has 32.