GPT-5.3-Codex (Codex Harness)
62±1
60interval63
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 10 min10 minutes ago
All sources syncing normally
- Arena · Text· 2 hours ago
- Arena · WebDev· 2 hours ago
- Arena · Vision· 2 hours ago
- Arena · Agent· 2 hours ago
- GPQA Diamond· 10 minutes ago
- SWE-bench· 10 minutes ago
- Terminal-Bench· 10 minutes ago
- ARC-AGI-2· 10 minutes ago
Filter by org:
Released:
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 | Interval | Swing | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | Add to compare | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 109 | GPT-5.3-Codex (Codex Harness) | openai | Oct 2026 | $1.75 / $14 | 61.7 73.5Ranked 61.7 = (3 × 73.5 + 3 × 50) ÷ 6. 73.5 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 60–63 | 49 | 3/22 | #29–236 | — | 42 | — | — | — | — | — | — | — | — | — | — | — | — | 88 | — | — | — | — | — | 91 | — |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model