Model comparison
Mistral Small 3 vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 31.2 on the Noometry Index. Mistral Small 3 costs 23× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Mistral Small 3 scores higher in 0 categories and Qwen3.5 397B-A17B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 397B-A17B leads 62.3 to 32.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for Mistral Small 3 and 88.9% for Qwen3.5 397B-A17B.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B accepts more context: 262K tokens versus 33K.
Side by side
| Mistral Small 3 | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.2 | 46.0 |
| Released | 2025-01-30 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 33K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.05 | $0.60 |
| Output $ / M tokens | $0.08 | $3.60 |
| Results tracked | 24 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Mistral Small 3: 36.5 (#207), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | Mistral Small 3 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1246 | 1465 |
| LMArena WebDev | — | 1400 |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
Agentic & Tool Use Not comparable
Mistral Small 3: —, Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Mistral Small 3 | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning Qwen3.5 397B-A17B leads
Mistral Small 3: 18.9 (#273), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Mistral Small 3 | Qwen3.5 397B-A17B |
|---|---|---|
| Chess Puzzles | 0% | 13% |
| LMArena Hard Prompts | 1233 | 1448 |
| Epoch Capabilities Index | 127.07 | 146.65 |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| Thematic Generalization | — | 65.1% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
Math Qwen3.5 397B-A17B leads
Mistral Small 3: 16.3 (#295), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Mistral Small 3 | Qwen3.5 397B-A17B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 88.9% |
| LMArena Math | 1240 | 1454 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
Knowledge Qwen3.5 397B-A17B leads
Mistral Small 3: 25.1 (#263), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Mistral Small 3 | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 47.3% | 86.4% |
| LMArena Expert | 1202 | 1462 |
| Confabulations | 25.2% | — |
Multimodal Not comparable
Mistral Small 3: —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Mistral Small 3 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual Qwen3.5 397B-A17B leads
Mistral Small 3: 37.3 (#236), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Mistral Small 3 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1198 | 1430 |
| LMArena Chinese | 1204 | 1500 |
| LMArena French | 1203 | 1461 |
| LMArena German | 1211 | 1447 |
| LMArena Japanese | 1111 | 1426 |
| LMArena Korean | 1188 | 1384 |
| LMArena Russian | 1216 | 1429 |
| LMArena Spanish | — | 1441 |
Instruction Following Qwen3.5 397B-A17B leads
Mistral Small 3: 63.7 (#229), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Mistral Small 3 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1214 | 1424 |
Long Context Qwen3.5 397B-A17B leads
Mistral Small 3: 37.8 (#211), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Mistral Small 3 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1246 | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
Mistral Small 3: 32.2 (#280), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Mistral Small 3 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1234 | 1438 |
| LMArena Creative Writing | 1195 | 1401 |
| EQ-Bench Creative Writing | 707 | 1478 |
| LMArena Multi-Turn | 1217 | 1446 |
Frequently asked questions
Is Mistral Small 3 better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 31.2 on the Noometry Index. Mistral Small 3 costs 23× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Which is cheaper, Mistral Small 3 or Qwen3.5 397B-A17B?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.
Is Mistral Small 3 or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 397B-A17B does, with 262K tokens against 33K.
How many benchmarks do Mistral Small 3 and Qwen3.5 397B-A17B share?
21 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen3.5 397B-A17B has 36.