Qwen3.5-27B
Qwen3.5-27B.
Qwen Released 24 Feb 2026 26
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Feb 2026 Qwen3.5-27B
Open weights
No Epoch Capabilities Index score yet
- Toolathlon 31.5% #30 /50
- MathArena (Apex, IMO, USAMO) 2.08% #33 /47
- LiveClawBench 31.6% #17 /17
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 | |
|---|---|---|---|---|
| MMLU-Pro | 86.1% | #25 of 212 | Official leaderboard | |
| Judgemark v2.1 | 84.3 | #9 of 42 | Official leaderboard | |
| SEA-HELM | 74.2 | #17 of 62 | Official leaderboard | |
| LMArena (Elo) | 1,409 | #120 of 333 | Official leaderboard | |
| Judgemark v4 | 60.5 | #19 of 40 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 59.0 | #65 of 119 | Official leaderboard | |
| Extended NYT Connections | 47.9% | #66 of 97 | Official leaderboard | |
| Vectara Hallucination Leaderboard (2025 dataset) | 12.1% | #81 of 104 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| DTBench | 70.7% | #80 of 178 | Official leaderboard | |
| MathArena (Apex, IMO, USAMO) | 2.08% | #33 of 47 | Official leaderboard | |
| AIME 2026 | 91.7% | #26 of 31 | Official leaderboard | |
| HMMT 2026 | 81.1% | #27 of 31 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WeirdML | 39.5% | #81 of 130 | Epoch AI | |
| WebDev Arena | 1,357 | #80 of 105 | Epoch AI | |
| Code Arena | 1,358 | #95 of 124 | Official leaderboard | |
| ALE-Bench | 349 | #107 of 121 | Epoch AI |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 31 | #31 of 183 | Official leaderboard | |
| Toolathlon | 31.5% | #30 of 50 | Official leaderboard | |
| LiveClawBench | 31.6% | #17 of 17 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vending-Bench 2 | $202 | #58 of 66 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MATH-Vision (MathVision) | 86% | #11 of 105 | Official leaderboard | |
| VideoMME v2 (with subtitles) | 31.4% | #8 of 31 | Official leaderboard | |
| Vision Arena | 1,217 | #66 of 136 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Conceptual Reasoning Index | 46.6 | #78 of 149 | Official leaderboard | |
| LMCA | 34% | #74 of 139 | Epoch AI | |
| ACCoRD | 60.5 | #88 of 150 | Official leaderboard |