GPT-5.4 (High, Codex Harness)
1,464±19
1,445CI1,483
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 20 min20 minutes ago
All sources syncing normally
- Arena · Text· 5 hours ago
- Arena · WebDev· 5 hours ago
- Arena · Vision· 5 hours ago
- Arena · Agent· 5 hours ago
- GPQA Diamond· 20 minutes ago
- SWE-bench· 20 minutes ago
- Terminal-Bench· 20 minutes ago
- ARC-AGI-2· 20 minutes ago
Filter by org:
Released:
GPT-5.4 mini (High)
1,398±7
1,391CI1,404
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 62 | GPT-5.4 (High, Codex Harness) | openai | Sep 2026 | $2.50 / $15 | 1,464 | 1,445–1,483 | #12–27 | ||
| 87 | GPT-5.4 mini (High) | openai | Oct 2026 | $0.75 / $4.50 | 1,398 | 1,391–1,404 | #75–180 |
Showing WebDev Arena exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.