Qwen3.6 35B A3B TEE
Qwen3.6 35B A3B is an open-weight MoE model from Alibaba's Qwen team with 35B total parameters and 3B active parameters per token. Running inside a TEE (Trusted Execution Environment), with provider attestation support.
Added Jun 9, 2026
Model weightsPricing
Auto routing · per 1M tokens- Input
- $0.20
- Output
- $1.27
- Cache read
- $0.056
Specifications
- Context window
- 262.1K
- Max output
- 262.1K
- Parameters
- 35B / 3B
- Total / active
Benchmarks
Benchmarks
Leaderboard results
These leaderboards tested Qwen3.6 35B A3B, another version of this model.
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 17, 2026 | ||
Epoch Capabilities Index | 144.0 | #85 of 115 |
FrontierMath v2 (Tiers 1–3) | 20.4% | #74 of 83 |
GPQA Diamond | 84.8% | #70 of 119 |
OTIS Mock AIME 2024–2025 | 86.7% | #69 of 121 |
Mystery Game Puzzles | 22.0% | #45 of 77 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 21.5 | #125 of 149 |
UGI Willingness | 2.2 | #118 of 149 |
UGI Writing | 45.4 | #67 of 149 |
Filtered and ranked to models on NanoGPT.
Providers
Provider information for this model’s automatic routing. These routes cannot be selected individually.
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
Recommended | $0.20 | $1.27 | $0.056 | N/A | N/A |
| $0.20 | $1.27 | $0.056 | N/A | N/A |