gpt-5.4-nano-2026-03-17
96.9%
no interval published
aiqbench · LLM benchmarks
96.9%
no interval published
94.5%
no interval published
93.0%
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-5.4-nano-2026-03-17 | openai | Oct 2026 | $0.20 / $1.25 | 96.9% | — | #95–222 | ||
| 19 | gpt-5.4-mini-2026-03-17 | openai | Oct 2026 | $0.75 / $4.50 | 94.5% | — | #75–180 | ||
| 33 | gpt-5.4-2026-03-05 | openai | Sep 2026 | $2.50 / $15 | 93.0% | — | #12–29 | ||
| 42 | gpt-5.4-pro-2026-03-05 | openai | Mar 2026 | $30 / $180 | 91.7% | — | #20–171 |
Showing HHEM Hallucination (Vectara) exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.