gpt-5.5-xhigh
79.9%
no interval published
aiqbench · LLM benchmarks
79.9%
no interval published
79.3%
no interval published
78.2%
no interval published
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 2 | gpt-5.5-xhigh | OpenAI | Sep 2026 | $5 / $30 | 79.9% | — | #9–34 | ||
| 4 | gpt-5-high | OpenAI | Aug 2025 | $1.25 / $10 | 79.3% | — | #64–149 | ||
| 7 | gpt-5-codex | OpenAI | — | — | 78.2% | — | #17–142 | ||
| 9 | gpt-5.4-xhigh | OpenAI | Sep 2026 | $2.50 / $15 | 78.0% | — | #12–27 | ||
| 17 | gpt-5.1-codex-max | OpenAI | Oct 2026 | $1.25 / $10 | 75.6% | — | #53–375 | ||
| 24 | gpt-5-pro-2025-10-06 | OpenAI | Oct 2025 | $15 / $120 | 74.7% | — | #88–166 | ||
| 26 | gpt-5.2-2025-12-11-high | OpenAI | Dec 2025 | $1.75 / $14 | 74.6% | — | #34–93 | ||
| 29 | gpt-5.2-codex | OpenAI | Oct 2026 | $1.75 / $14 | 74.0% | — | #37–370 | ||
| 30 | gpt-5.1-2025-11-13-high | OpenAI | Nov 2025 | $1.25 / $10 | 73.9% | — | #45–242 | ||
| 36 | gpt-5.3-codex-high | OpenAI | Oct 2026 | $1.75 / $14 | 72.8% | — | #29–236 | ||
| 55 | gpt-5-mini-high | OpenAI | Aug 2025 | $0.25 / $2 | 69.8% | — | #126–343 | ||
| 56 | gpt-5.4-nano-xhigh | OpenAI | Oct 2026 | $0.20 / $1.25 | 69.6% | — | #94–222 | ||
| 71 | gpt-5.4-mini-xhigh | OpenAI | Oct 2026 | $0.75 / $4.50 | 66.4% | — | #75–180 | ||
| 76 | gpt-5.1-codex-mini | OpenAI | Oct 2026 | $0.25 / $2 | 65.7% | — | #54–425 | ||
| 105 | gpt-5-chat | OpenAI | Aug 2025 | — | 61.0% | — | #92–310 | ||
| 114 | gpt-5.3-instant | OpenAI | — | — | 60.0% | — | — | ||
| 135 | gpt-5-nano | OpenAI | Aug 2025 | $0.05 / $0.40 | 55.0% | — | #132–399 | ||
| 144 | gpt-5.2-2025-12-11-nothinking | OpenAI | — | — | 53.8% | — | — | ||
| 182 | gpt-5.1-2025-11-13-nothinking | OpenAI | — | — | 47.5% | — | — |
Showing LiveBench exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.