Qwen3.6 27B Thinking
Qwen3.6 27B is a native vision-language dense model with stronger agentic coding and STEM reasoning than Qwen 3.5 27B. It also improves spatial intelligence (including object localization/detection), plus video understanding, document OCR, and visual-agent workflows.
- Reasoning
- Vision
- Video Input
Added Apr 23, 2026
Model weightsPricing
Auto routing · per 1M tokens- Input
- $0.203
- Output
- $2.24
- Cache read
- $0.102
Specifications
- Context window
- 262.1K
- Max output
- 65.5K
- Parameters
- 27B
Benchmarks
Benchmarks
Leaderboard results
These leaderboards tested Qwen3.6 27B, 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 | 146.7 | #76 of 115 |
FrontierMath v2 (Tiers 1–3) | 35.1% | #63 of 83 |
GPQA Diamond | 85.9% | #66 of 119 |
OTIS Mock AIME 2024–2025 | 91.1% | #57 of 121 |
Mystery Game Puzzles | 7.0% | #75 of 77 |
EQ-Bench 4 | 1015 | #30 of 31 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 27.1 | #113 of 149 |
UGI Willingness | 2.8 | #93 of 149 |
UGI Writing | 42.5 | #78 of 149 |
Filtered and ranked to models on NanoGPT.
Providers
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
| $0.203 | $2.24 | $0.102 | N/A | N/A | |
| $0.203 | $2.24 | $0.102 | N/A | N/A | |
| $0.203 | $2.24 | N/A | N/A | N/A | |
| $0.263 | $2.10 | $0.0262 | N/A | N/A | |
| $0.315 | $3.36 | N/A | N/A | N/A | |
| $0.336 | $3.36 | N/A | N/A | N/A | |
| $0.355 | $3.49 | N/A | N/A | N/A | |
| $0.63 | $3.78 | N/A | N/A | N/A | |
| $0.63 | $3.78 | N/A | N/A | N/A |
Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.