gpt-5.4-2026-03-05
97.8%±2.2%
95.6%CI100.0%
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 9 min9 minutes ago
All sources syncing normally
- Arena · Text· 3 hours ago
- Arena · WebDev· 3 hours ago
- Arena · Vision· 3 hours ago
- Arena · Agent· 3 hours ago
- GPQA Diamond· 9 minutes ago
- SWE-bench· 9 minutes ago
- Terminal-Bench· 9 minutes ago
- ARC-AGI-2· 9 minutes ago
Filter by org:
Released:
gpt-5.4-mini-2026-03-17
88.9%±4.7%
84.2%CI93.6%
gpt-5.4-nano-2026-03-17
87.8%±3.9%
83.8%CI91.7%
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 30 | gpt-5.4-2026-03-05 | OpenAI | Sep 2026 | $2.50 / $15 | 97.8% | 95.6%–100.0% | #12–29 | ||
| 60 | gpt-5.4-mini-2026-03-17 | OpenAI | Oct 2026 | $0.75 / $4.50 | 88.9% | 84.2%–93.6% | #75–180 | ||
| 66 | gpt-5.4-nano-2026-03-17 | OpenAI | Oct 2026 | $0.20 / $1.25 | 87.8% | 83.8%–91.7% | #95–222 |
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.