Qwen 3.6 Flash
Qwen 3.6 Flash.
22
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Apr 2026 Qwen 3.6 Flash
143.7
#105 of 256
Epoch Capabilities Index
- GPQA Diamond 83.3% #88 /229
- FrontierMath 10.3% #31 /55
- FrontierMath Tier 4 0% #55 /55
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenAI MRCR v2 | 38.1% | #29 of 47 | Official leaderboard | |
| Judgemark v4 | 31.2 | #34 of 40 | Official leaderboard | |
| SimpleQA Verified | 15.9% | #85 of 94 | Epoch AI run |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 83.3% | #88 of 229 | Epoch AI run | |
| OTIS Mock AIME 2024-2025 | 84.4% | #90 of 212 | Epoch AI run | |
| DTBench | 77.1% | #100 of 180 | Official leaderboard | |
| FrontierMath | 10.3% | #31 of 55 | Official leaderboard | |
| SimpleBench | 35.2% | #79 of 106 | Official leaderboard | |
| FrontierMath Tiers 1-3 v2 | 22.5% | #73 of 86 | Official leaderboard | |
| FrontierMath Tier 4 | 0% | #55 of 55 | Epoch AI run |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ALE-Bench | 1,015 | #106 of 126 | Official leaderboard | |
| Claw-SWE-Bench | 62.8% | #14 of 16 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| PinchBench 2.0 | 88.1% | #8 of 57 | Official leaderboard | |
| LiveClawBench | 70.2% | #8 of 17 | Official leaderboard | |
| Mystery Game Puzzles | 18% | #57 of 84 | Epoch AI run | |
| ClawProBench | 56.5% | #35 of 49 | Official leaderboard | |
| SnakeBench | 17 | #163 of 188 | Official leaderboard | |
| Chess Puzzles | 12% | #82 of 93 | Epoch AI run |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| nocot-bench (NCRI) | 63.3 | #128 of 185 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ACCoRD | 61.5 | #87 of 152 | Official leaderboard | |
| LMCA | 31% | #87 of 147 | Official leaderboard | |
| Conceptual Reasoning Index | 43.3 | #90 of 151 | Official leaderboard |
Qwen's models over time
Qwen's models in color, against every other model on the Epoch Capabilities Index, by release date.
Source: Epoch Capabilities Index, Epoch AI (CC BY 4.0)