Model comparison
Mistral Small vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 33.4 on the Noometry Index. Mistral Small costs 5.1× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
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 397B-A17B in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5 397B-A17B leads 46.1 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 5.8% for Mistral Small and 88.9% for Qwen3.5 397B-A17B.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
Side by side
| Mistral Small | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 46.0 |
| Released | 2024-02-26 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 256K | 66K |
| Input $ / M tokens | $0.15 | $0.60 |
| Output $ / M tokens | $0.60 | $3.60 |
| Results tracked | 39 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Mistral Small: 34.0 (#247), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | Mistral Small | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1362 | 1465 |
| LMArena WebDev | — | 1400 |
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Qwen3.5 397B-A17B leads
Mistral Small: 28.1 (#93), Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Mistral Small | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| Berkeley Function Calling Leaderboard | 37.1% | — |
| 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: 19.8 (#250), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Mistral Small | Qwen3.5 397B-A17B |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 73.7% |
| LMArena Hard Prompts | 1335 | 1448 |
| DTBench | 70.9% | 87.5% |
| LMCA | 20.6% | 37.9% |
| NYT Connections (extended) | — | 58.9% |
| CritPt | 0% | — |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| LiveBench Reasoning | 44.8% | — |
| Mystery Game Puzzles | — | 18% |
| LiveBench Data Analysis | 53.7% | — |
| Epoch Capabilities Index | — | 146.65 |
| LiveBench | 44% | — |
Math Qwen3.5 397B-A17B leads
Mistral Small: 16.4 (#293), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Mistral Small | Qwen3.5 397B-A17B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 88.9% |
| LMArena Math | 1341 | 1454 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| LiveBench Math | 39.9% | — |
| MATH Level 5 | 46.8% | — |
Knowledge Qwen3.5 397B-A17B leads
Mistral Small: 31.0 (#222), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Mistral Small | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 47.5% | 86.4% |
| LMArena Expert | 1291 | 1462 |
| Vectara Hallucination Rate | 5.1% | — |
| MMLU | 68.7% | — |
Multimodal Qwen3.5 397B-A17B leads
Mistral Small: 33.5 (#96), Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Mistral Small | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | 1142 | 1263 |
Multilingual Qwen3.5 397B-A17B leads
Mistral Small: 45.5 (#169), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Mistral Small | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1315 | 1430 |
| LMArena Chinese | 1340 | 1500 |
| LMArena French | 1337 | 1461 |
| LMArena German | 1340 | 1447 |
| LMArena Japanese | 1275 | 1426 |
| LMArena Korean | 1259 | 1384 |
| LMArena Russian | 1324 | 1429 |
| LMArena Spanish | 1346 | 1441 |
Instruction Following Qwen3.5 397B-A17B leads
Mistral Small: 66.4 (#209), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Mistral Small | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1310 | 1424 |
| LiveBench Instruction Following | 63.7% | — |
Long Context Qwen3.5 397B-A17B leads
Mistral Small: 40.4 (#156), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Mistral Small | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1327 | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
Mistral Small: 52.5 (#171), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Mistral Small | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1338 | 1438 |
| LMArena Creative Writing | 1305 | 1401 |
| LMArena Multi-Turn | 1344 | 1446 |
| EQ-Bench Creative Writing | — | 1478 |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 33.4 on the Noometry Index. Mistral Small costs 5.1× 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 or Qwen3.5 397B-A17B?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.
Is Mistral Small or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Mistral Small and Qwen3.5 397B-A17B share?
23 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen3.5 397B-A17B has 36.