Qwen3.8-2.4T-A95B
Qwen3.8-2.4T-A95B.
12
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Aug 2026 Qwen3.8-2.4T-A95B
Open weights Flagship
No Epoch Capabilities Index score yet
- Human Pathogen Capabilities Test v2 (HPCT v2) 57.9% #31 /71
- WitnessBench 5.00% #9 /12
- ArXivLean 1.89% #7 /7
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 | |
|---|---|---|---|---|
| Creative Writing v3 | 76.5 | #27 of 120 | Official leaderboard |
Math and science
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WeirdML | 75.2% | #17 of 112 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MCP Atlas | 84.5% | #4 of 34 | Official leaderboard | |
| WitnessBench | 5.00% | #9 of 12 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ArtifactArena | 1,055 | #12 of 21 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| DistressBench | 77.5% | #8 of 42 | Official leaderboard | |
| Human Pathogen Capabilities Test v2 (HPCT v2) | 57.9% | #31 of 71 | Official leaderboard | |
| FORTRESS | 21.6% | #30 of 66 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Conceptual Reasoning Index | 59.4 | #36 of 149 | Official leaderboard | |
| ACCoRD | 71.6 | #37 of 150 | Official leaderboard |