Model comparison
Mistral Small 3 vs Qwen3.5-Flash
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 31.2 on the Noometry Index. Mistral Small 3 costs 3.0× less per token, which makes it the better buy when Qwen3.5-Flash's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Mistral Small 3 scores higher in 1 category and Qwen3.5-Flash in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5-Flash leads 57.9 to 32.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for Mistral Small 3 and 84.4% for Qwen3.5-Flash.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.10 / $0.40 for Qwen3.5-Flash.
- Qwen3.5-Flash accepts more context: 1M tokens versus 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Small 3 | Qwen3.5-Flash | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.2 | 42.5 |
| Released | 2025-01-30 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | 33K | 1M |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.05 | $0.10 |
| Output $ / M tokens | $0.08 | $0.40 |
| Results tracked | 24 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
Mistral Small 3: 36.5 (#207), Qwen3.5-Flash: 34.2 (#242)
| Benchmark | Mistral Small 3 | Qwen3.5-Flash |
|---|---|---|
| LMArena Coding | 1246 | 1412 |
| LMArena WebDev | — | 1244 |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
| ALE-Bench | — | 221.8 |
Agentic & Tool Use Not comparable
Mistral Small 3: —, Qwen3.5-Flash: —
| Benchmark | Mistral Small 3 | Qwen3.5-Flash |
|---|---|---|
| Vending-Bench 2 | — | 462.69 |
Reasoning Qwen3.5-Flash leads
Mistral Small 3: 18.9 (#273), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | Mistral Small 3 | Qwen3.5-Flash |
|---|---|---|
| Chess Puzzles | 0% | 21% |
| LMArena Hard Prompts | 1233 | 1403 |
| Epoch Capabilities Index | 127.07 | 143.98 |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 82.9% |
| LMCA | — | 29.1% |
Math Qwen3.5-Flash leads
Mistral Small 3: 16.3 (#295), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | Mistral Small 3 | Qwen3.5-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 84.4% |
| LMArena Math | 1240 | 1407 |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3.5-Flash leads
Mistral Small 3: 25.1 (#263), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | Mistral Small 3 | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 47.3% | 82.3% |
| LMArena Expert | 1202 | 1407 |
| SimpleQA Verified | — | 20.3% |
| Confabulations | 25.2% | — |
| Vectara Hallucination Rate | — | 10.5% |
Multilingual Qwen3.5-Flash leads
Mistral Small 3: 37.3 (#236), Qwen3.5-Flash: 50.5 (#121)
| Benchmark | Mistral Small 3 | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1198 | 1385 |
| LMArena Chinese | 1204 | 1446 |
| LMArena French | 1203 | 1412 |
| LMArena German | 1211 | 1390 |
| LMArena Japanese | 1111 | 1368 |
| LMArena Korean | 1188 | 1344 |
| LMArena Russian | 1216 | 1379 |
| LMArena Spanish | — | 1400 |
Instruction Following Qwen3.5-Flash leads
Mistral Small 3: 63.7 (#229), Qwen3.5-Flash: 72.6 (#139)
| Benchmark | Mistral Small 3 | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1214 | 1374 |
Long Context Qwen3.5-Flash leads
Mistral Small 3: 37.8 (#211), Qwen3.5-Flash: 42.4 (#124)
| Benchmark | Mistral Small 3 | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1246 | 1392 |
Writing & Preference Qwen3.5-Flash leads
Mistral Small 3: 32.2 (#280), Qwen3.5-Flash: 57.9 (#122)
| Benchmark | Mistral Small 3 | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1234 | 1397 |
| LMArena Creative Writing | 1195 | 1343 |
| LMArena Multi-Turn | 1217 | 1393 |
| EQ-Bench Creative Writing | 707 | — |
Frequently asked questions
Is Mistral Small 3 better than Qwen3.5-Flash?
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 31.2 on the Noometry Index. Mistral Small 3 costs 3.0× less per token, which makes it the better buy when Qwen3.5-Flash's lead doesn't matter for your workload.
Which is cheaper, Mistral Small 3 or Qwen3.5-Flash?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen3.5-Flash lists at $0.10 and $0.40.
Is Mistral Small 3 or Qwen3.5-Flash better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5-Flash does, with 1M tokens against 33K.
How many benchmarks do Mistral Small 3 and Qwen3.5-Flash share?
20 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen3.5-Flash has 32.