claude-sonnet-4-6
32.4%±2.8%
29.6%CI35.2%
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 15 min15 minutes ago
All sources syncing normally
- Arena · Text· 4 hours ago
- Arena · WebDev· 4 hours ago
- Arena · Vision· 4 hours ago
- Arena · Agent· 4 hours ago
- GPQA Diamond· 15 minutes ago
- SWE-bench· 15 minutes ago
- Terminal-Bench· 15 minutes ago
- ARC-AGI-2· 15 minutes ago
Filter by org:
Released:
claude-sonnet-4-5-20250929
15.2%±2.1%
13.1%CI17.3%
claude-sonnet-4-20250514
4.1%±1.2%
3.0%CI5.3%
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 17 | claude-sonnet-4-6 | Anthropic | Sep 2026 | $3 / $15 | 32.4% | 29.6%–35.2% | #38–77 | ||
| 34 | claude-sonnet-4-5-20250929 | Anthropic | Sep 2025 | $3 / $15 | 15.2% | 13.1%–17.3% | #66–232 | ||
| 51 | claude-sonnet-4-20250514 | Anthropic | May 2025 | — | 4.1% | 3.0%–5.3% | #78–436 |
Showing FrontierMath exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.