hy3
1,507±8
1,498CI1,515
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 47 min47 minutes ago
All sources syncing normally
- Arena · Text· 3 hours ago
- Arena · WebDev· 3 hours ago
- Arena · Vision· 3 hours ago
- Arena · Agent· 3 hours ago
- GPQA Diamond· 47 minutes ago
- SWE-bench· 47 minutes ago
- Terminal-Bench· 47 minutes ago
- ARC-AGI-2· 47 minutes ago
Filter by org:
Released:
Hy3 preview
1,357±17
1,339CI1,374
hunyuan-hy3-preview
1,357±17
1,339CI1,374
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 53 | hy3 | tencent | Jul 2026 | $0.08 / $0.33 | 1,507 | 1,498–1,515 | #65–318 | ||
| 105 | Hy3 preview | tencent | Apr 2026 | $0.18 / $0.60 | 1,357 | 1,339–1,374 | #111–432 | ||
| 106 | hunyuan-hy3-preview | tencent | Oct 2026 | — | 1,357 | 1,339–1,374 | #116–632 |
Showing WebDev Arena exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.