claude-opus-4-8
98.3%±1.4%
96.9%CI99.7%
aiqbench · LLM benchmarks
98.3%±1.4%
96.9%CI99.7%
97.8%±2.2%
95.6%CI100.0%
94.4%±2.8%
91.6%CI97.3%
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 23 | claude-opus-4-8 | Anthropic | Sep 2026 | $5 / $25 | 98.3% | 96.9%–99.7% | #15–33 | ||
| 29 | claude-opus-4-7 | Anthropic | Sep 2026 | $5 / $25 | 97.8% | 95.6%–100.0% | #1–18 | ||
| 43 | claude-opus-4-6 | Anthropic | Sep 2026 | $5 / $25 | 94.4% | 91.6%–97.3% | #2–25 | ||
| 74 | claude-opus-4-5-20251101 | Anthropic | Nov 2025 | $5 / $25 | 86.1% | 81.8%–90.4% | #19–62 | ||
| 102 | claude-opus-4-1-20250805 | Anthropic | Aug 2025 | $15 / $75 | 68.9% | 61.9%–75.9% | #73–404 | ||
| 110 | claude-opus-4-20250514 | Anthropic | May 2025 | — | 64.4% | 57.2%–71.7% | #84–470 |
Showing AIME (math) exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.