claude-opus-4-8
91.0%±1.9%
89.1%CI93.0%
aiqbench · LLM benchmarks
91.0%±1.9%
89.1%CI93.0%
90.5%±1.7%
88.8%CI92.2%
90.2%±1.8%
88.3%CI92.0%
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 29 | claude-opus-4-8 | Anthropic | Sep 2026 | $5 / $25 | 91.0% | 89.1%–93.0% | #15–33 | ||
| 38 | claude-opus-4-6 | Anthropic | Sep 2026 | $5 / $25 | 90.5% | 88.8%–92.2% | #2–25 | ||
| 41 | claude-opus-4-7 | Anthropic | Sep 2026 | $5 / $25 | 90.2% | 88.3%–92.0% | #1–18 | ||
| 66 | claude-opus-4-5-20251101 | Anthropic | Nov 2025 | $5 / $25 | 86.0% | 84.0%–88.1% | #19–62 | ||
| 93 | claude-opus-4-1-20250805 | Anthropic | Aug 2025 | $15 / $75 | 77.3% | 74.3%–80.3% | #73–404 | ||
| 97 | claude-opus-4-20250514 | Anthropic | May 2025 | — | 76.3% | 73.2%–79.3% | #84–470 |
Showing GPQA Diamond exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.