Gemini 3.0 Flash leads on the shared-benchmark average
Ahead on 7 of 8 shared benchmarks, averaging 4.8 points higher
Summarised only from the 8 percentage-scale benchmarks scored by every selected model; details are below.
“Best available” takes each model’s best recorded non-parallel result in the metric’s stated direction per benchmark, so it may combine modes into a virtual configuration that does not exist. Read it with the mode breakdown.

Qwen3.6-27B
阿里巴巴
Benchmark-by-benchmark comparison. Changing the thinking mode or tool filters updates the chart and table below.
“Best available” picks the best non-parallel result in the metric’s stated direction separately for each benchmark. The resulting series can combine several reasoning levels and is not one reproducible runtime configuration. Choose a mode filter to compare like-for-like runs.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Each axis is the mean percentage score of one benchmark domain. It is an average, not a capability rating.
Relative edge: AI Agent - 工具使用 +4.9 / Relative gap: 指令跟随 -9.9
Relative edge: 指令跟随 +9.9 / Relative gap: AI Agent - 工具使用 -4.9
Method: for each model and benchmark, all scores in the current mode scope are averaged (not the best score), then those benchmark scores are averaged within each domain. Only benchmarks scored on a 0-100 scale by at least two of the selected models count — Elo and rating-scale benchmarks such as Codeforces or Arena are excluded, because averaging a 1500 rating with an 85% accuracy produces a meaningless number. Missing values are not counted as zero, and the averages are unweighted, so domains with harder benchmarks read lower.
Every model and runtime mode, benchmark by benchmark. Values are comparable along a row, not between different benchmarks.
15 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Qwen3.6-27B | Gemini 3.0 Flash |
|---|---|---|
1.10Thinking Enabled | 8.60Thinking Enabled | |
24.00Thinking Enabled | 43.50Thinking Enabled | Tools | |
64.03Standard Mode | 72.40Thinking Level · High | |
87.80Thinking Enabled | 90.40Thinking Enabled | |
83.90Thinking Enabled | 90.80Thinking Enabled | |
53.50Thinking Enabled | Tools | 49.60Thinking Level · High | Tools | |
77.20Thinking Enabled | Tools | 68.70Thinking Enabled | |
34.80Thinking Enabled | Tools | 38.60Thinking Enabled | Tools | |
94.20Thinking Enabled | Tools | 91.23Thinking Level · High | Tools | |
16.70Thinking Enabled | Tools | 27.32Thinking Level · High | Tools | |
67.60Thinking Enabled | 78.00Thinking Enabled | |
59.30Thinking Enabled | Tools | 47.60Thinking Enabled | Tools | |
60.70Thinking Enabled | Tools | 58.00Thinking Level · High | Tools | |
72.40Thinking Enabled | Tools | 85.70Thinking Enabled | Tools | |
74.60Thinking Enabled | 79.90Thinking Enabled |
Official list prices per model API, split by input and output. Unit: USD per 1M tokens.
Architecture, licensing and API modalities. "Not provided" means the field is missing from our database.
| Features & specs | Qwen3.6-27B阿里巴巴 | Gemini 3.0 FlashGoogle Deep Mind |
|---|---|---|
Core specsRelease | 2026-04-22 | 2025-12-17 |
Context length | 128K | 2000K |
Total parameters | 27B | — |
Max output length | 16,384 tokens | 65,536 tokens |
Architecture | Dense | Undisclosed |
Runtime modes | 关闭开启 | 关闭16K32K4K64K8K开启深度 |
Availability & licensingCode availability | Available · Qwen License | Not public |
Weight availability | Available · Qwen License | Not public |
Use & commercial terms | 免费商用授权 | Official service only; subject to provider terms |
Local deploymentWeights | Hugging Face | Not provided |
API modality supportText Input/Output | Input:YesOutput:Yes | Input:YesOutput:Yes |
Image Input/Output | Input:YesOutput:No | Input:YesOutput:No |
Audio Input/Output | Input:NoOutput:No | Input:YesOutput:No |
Video Input/Output | Input:YesOutput:No | Input:YesOutput:No |
ResourcesPaper / report | Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model | Gemini 3 Flash: frontier intelligence built for speed |
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 | Gemini 3 Flash:Google 在 12 月 17 日发布的新一代默认模型 |

Gemini 3.0 Flash
Google Deep Mind