Model comparison
Qwen3.6 35B-A3B vs Qwen3 8B
Qwen3.6 35B-A3B is the stronger model overall, scoring 37.6 to 33.7 on the Noometry Index. Qwen3 8B costs 1.8× less per token, which makes it the better buy when Qwen3.6 35B-A3B's lead doesn't matter for your workload.
Last verified . 8 shared benchmarks.
Alibaba (Qwen)Summary
- They share 8 benchmarks with published results for both. Qwen3.6 35B-A3B scores higher in 4 categories and Qwen3 8B in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 35B-A3B leads 51.3 to 36.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.7% for Qwen3.6 35B-A3B and 56.1% for Qwen3 8B.
- Qwen3 8B is cheaper at $0.18 / $0.70 per million input/output tokens, against $0.25 / $1.49 for Qwen3.6 35B-A3B.
- Qwen3.6 35B-A3B accepts more context: 262K tokens versus 131K.
Side by side
| Qwen3.6 35B-A3B | Qwen3 8B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 37.6 | 33.7 |
| Released | 2026-04-01 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 66K | 8K |
| Input $ / M tokens | $0.25 | $0.18 |
| Output $ / M tokens | $1.49 | $0.70 |
| Results tracked | 14 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 35B-A3B leads
Qwen3.6 35B-A3B: 37.2 (#196), Qwen3 8B: 34.0 (#248)
Agentic & Tool Use Qwen3 8B leads
Qwen3.6 35B-A3B: 22.1 (#134), Qwen3 8B: 30.2 (#78)
| Benchmark | Qwen3.6 35B-A3B | Qwen3 8B |
|---|---|---|
| Terminal-Bench | 23% | — |
| Berkeley Function Calling Leaderboard | — | 42.6% |
Reasoning Qwen3.6 35B-A3B leads
Qwen3.6 35B-A3B: 28.0 (#109), Qwen3 8B: 16.6 (#303)
| Benchmark | Qwen3.6 35B-A3B | Qwen3 8B |
|---|---|---|
| CritPt | 0.3% | 0% |
| Chess Puzzles | 26% | 5% |
| DTBench | 73.9% | 59.7% |
| LMCA | 29.7% | 8.8% |
| Epoch Capabilities Index | 143.93 | 136.17 |
| NYT Connections (extended) | 41.6% | — |
| Mystery Game Puzzles | 22% | — |
| Surface Evolver Bench | 44.4% | — |
Math Qwen3.6 35B-A3B leads
Qwen3.6 35B-A3B: 38.9 (#121), Qwen3 8B: 34.9 (#191)
| Benchmark | Qwen3.6 35B-A3B | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 56.1% |
| FrontierMath (Tiers 1-3) | 20.4% | — |
Knowledge Qwen3.6 35B-A3B leads
Qwen3.6 35B-A3B: 51.3 (#68), Qwen3 8B: 36.1 (#173)
| Benchmark | Qwen3.6 35B-A3B | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 84.8% | 56.8% |
| Vectara Hallucination Rate | — | 4.8% |
Long Context Not comparable
Qwen3.6 35B-A3B: —, Qwen3 8B: 37.9 (#210)
| Benchmark | Qwen3.6 35B-A3B | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
Frequently asked questions
Is Qwen3.6 35B-A3B better than Qwen3 8B?
Qwen3.6 35B-A3B is the stronger model overall, scoring 37.6 to 33.7 on the Noometry Index. Qwen3 8B costs 1.8× less per token, which makes it the better buy when Qwen3.6 35B-A3B's lead doesn't matter for your workload.
Which is cheaper, Qwen3.6 35B-A3B or Qwen3 8B?
Qwen3 8B is cheaper. It lists at $0.18 per million input tokens and $0.70 per million output tokens; Qwen3.6 35B-A3B lists at $0.25 and $1.49.
Is Qwen3.6 35B-A3B or Qwen3 8B better for coding?
Qwen3.6 35B-A3B scores higher on coding benchmarks: 37.2 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 35B-A3B does, with 262K tokens against 131K.
How many benchmarks do Qwen3.6 35B-A3B and Qwen3 8B share?
8 benchmarks have published results for both models. Qwen3.6 35B-A3B has 14 scored results on Noometry and Qwen3 8B has 11.