Model comparison
Mistral Small vs Qwen3.5 35B-A3B
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 33.4 on the Noometry Index. Mistral Small costs 2.6× less per token, which makes it the better buy when Qwen3.5 35B-A3B's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Mistral Small scores higher in 1 category and Qwen3.5 35B-A3B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5 35B-A3B leads 39.9 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 5.8% for Mistral Small and 70% for Qwen3.5 35B-A3B.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.25 / $2 for Qwen3.5 35B-A3B.
Side by side
| Mistral Small | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 42.0 |
| Released | 2024-02-26 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 256K | 66K |
| Input $ / M tokens | $0.15 | $0.25 |
| Output $ / M tokens | $0.60 | $2 |
| Results tracked | 39 | 28 |
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 35B-A3B: 33.8 (#251)
| Benchmark | Mistral Small | Qwen3.5 35B-A3B |
|---|---|---|
| SciCode | 26.5% | 29.3% |
| LMArena Coding | 1362 | 1410 |
| LMArena WebDev | — | 1254 |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Not comparable
Mistral Small: 28.1 (#93), Qwen3.5 35B-A3B: —
| Benchmark | Mistral Small | Qwen3.5 35B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
Reasoning Qwen3.5 35B-A3B leads
Mistral Small: 19.8 (#250), Qwen3.5 35B-A3B: 24.6 (#161)
| Benchmark | Mistral Small | Qwen3.5 35B-A3B |
|---|---|---|
| CritPt | 0% | 0.6% |
| LMArena Hard Prompts | 1335 | 1400 |
| DTBench | 70.9% | 80% |
| LMCA | 20.6% | 29.5% |
| Kagi LLM Benchmark | 37.8% | — |
| Chess Puzzles | — | 10% |
| LiveBench Reasoning | 44.8% | — |
| LiveBench Data Analysis | 53.7% | — |
| Epoch Capabilities Index | — | 142.52 |
| LiveBench | 44% | — |
Math Qwen3.5 35B-A3B leads
Mistral Small: 16.4 (#293), Qwen3.5 35B-A3B: 39.9 (#97)
| Benchmark | Mistral Small | Qwen3.5 35B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 70% |
| LMArena Math | 1341 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| LiveBench Math | 39.9% | — |
| MATH Level 5 | 46.8% | — |
Knowledge Qwen3.5 35B-A3B leads
Mistral Small: 31.0 (#222), Qwen3.5 35B-A3B: 47.8 (#79)
| Benchmark | Mistral Small | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | 47.5% | 83.5% |
| Vectara Hallucination Rate | 5.1% | 10.5% |
| LMArena Expert | 1291 | 1408 |
| MMLU | 68.7% | — |
Multimodal Not comparable
Mistral Small: 33.5 (#96), Qwen3.5 35B-A3B: —
| Benchmark | Mistral Small | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Qwen3.5 35B-A3B leads
Mistral Small: 45.5 (#169), Qwen3.5 35B-A3B: 50.0 (#127)
| Benchmark | Mistral Small | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1315 | 1378 |
| LMArena Chinese | 1340 | 1457 |
| LMArena French | 1337 | 1412 |
| LMArena German | 1340 | 1367 |
| LMArena Japanese | 1275 | 1325 |
| LMArena Korean | 1259 | 1356 |
| LMArena Russian | 1324 | 1376 |
| LMArena Spanish | 1346 | 1392 |
Instruction Following Qwen3.5 35B-A3B leads
Mistral Small: 66.4 (#209), Qwen3.5 35B-A3B: 72.8 (#128)
| Benchmark | Mistral Small | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1310 | 1379 |
| LiveBench Instruction Following | 63.7% | — |
Long Context Qwen3.5 35B-A3B leads
Mistral Small: 40.4 (#156), Qwen3.5 35B-A3B: 42.4 (#127)
| Benchmark | Mistral Small | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1327 | 1389 |
Writing & Preference Qwen3.5 35B-A3B leads
Mistral Small: 52.5 (#171), Qwen3.5 35B-A3B: 57.9 (#124)
| Benchmark | Mistral Small | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1338 | 1395 |
| LMArena Creative Writing | 1305 | 1346 |
| LMArena Multi-Turn | 1344 | 1390 |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 33.4 on the Noometry Index. Mistral Small costs 2.6× less per token, which makes it the better buy when Qwen3.5 35B-A3B's lead doesn't matter for your workload.
Which is cheaper, Mistral Small or Qwen3.5 35B-A3B?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen3.5 35B-A3B lists at $0.25 and $2.
Is Mistral Small or Qwen3.5 35B-A3B better for coding?
They score almost the same on coding (34.0 vs 33.8); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Mistral Small and Qwen3.5 35B-A3B share?
24 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen3.5 35B-A3B has 28.