See key specs and per-benchmark scores for each model/mode. Scroll horizontally for all columns. 当前对比 2 个模型的评测数据与核心参数。

Qwen3.6-27B
阿里巴巴
Each axis is a category average, normalized to a 100-point radar.
Relative edge: AI Agent - 工具使用 +17.7 / Relative gap: OpenClaw智能体能力综合测评 -2.8
Relative edge: OpenClaw智能体能力综合测评 +2.8 / Relative gap: AI Agent - 工具使用 -17.7
Method: for each model and benchmark, the chart first averages all scores in the current mode scope instead of taking the best score, then averages those benchmark scores within each category. Only benchmarks with at least two selected models scored are included; missing values are not counted as zero.
Best overall
Qwen3.6-27B · 72.77
Best single
Qwen3.6-27B · C-Eval 91.40
Modality coverage
Qwen3.6-27B · 0 modalities
Head to head
8
Benchmarks
6
Wins
2
Losses
+0.21
Average diff
Compare benchmark results across thinking modes and tool usage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Complete scores for each model/mode across selected benchmarks.
8 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Qwen3.6-27B | Qwen3.5-27B |
|---|---|---|
C-Eval 综合评估 | 91.40Thinking Enabled | 90.50Thinking Enabled |
GPQA Diamond 综合评估 | 87.80Thinking Enabled | 85.50Thinking Enabled |
HLE 综合评估 | 24.00Thinking Enabled | 48.50Thinking Enabled | Tools |
MMLU Pro 综合评估 | 86.20Thinking Enabled | 86.10Thinking Enabled |
LiveCodeBench 编程与软件工程 | 83.90Thinking Enabled | 80.70Thinking Enabled | Tools |
SWE-bench Verified 编程与软件工程 | 77.20Thinking Enabled | Tools | 72.40Thinking Enabled |
Terminal Bench 2.0 AI Agent - 工具使用 | 59.30Thinking Enabled | Tools | 41.60Thinking Enabled | Tools |
Claw Bench OpenClaw智能体能力综合测评 | 72.40Thinking Enabled | Tools | 75.20Thinking Enabled | Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Qwen3.6-27B阿里巴巴 | Qwen3.5-27B阿里巴巴 |
|---|---|---|
Core specsRelease | 2026-04-22 | 2026-02-25 |
Context length | 128K | 1010K |
Parameters | 270 | 270 |
Active parameters | 270 | 270 |
Max output | 16384 | 248320 |
MoE | No | No |
Supported modes | No mode data | 常规模式(Non-Thinking Mode)思考模式(Thinking Mode) |
LicenseCode Open Source | Not provided | Not provided |
Weights Open Source | Not provided | Not provided |
Commercial use | 免费商用授权 | 免费商用授权 |
ResourcesPaper / report | Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model | Qwen3.5: Towards Native Multimodal Agents |
DataLearner blog | 阿里正式开源Qwen3.6-27B:代码智能体能力上超越全面超越前代旗舰版本之 Qwen3.5-397B-A17B | Not provided |

Qwen3.5-27B
阿里巴巴