gpt-6-astra-max
83±3
79interval86
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,308
- Last sync
- 36 min36 minutes ago
All sources syncing normally
- Arena · Text· 10 hours ago
- Arena · WebDev· 10 hours ago
- Arena · Vision· 10 hours ago
- Arena · Agent· 10 hours ago
- GPQA Diamond· 36 minutes ago
- SWE-bench· 36 minutes ago
- Terminal-Bench· 36 minutes ago
- ARC-AGI-2· 36 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 | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 4 | gpt-6-astra-max | openai | Sep 2026 | $10 / $50 | 83.5 90.6Ranked 83.5 = (14 × 90.6 + 3 × 50) ÷ 17. 90.6 is the mean percentile over the 14 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 79–86 | 42 | 14/22 | #1–18 | 93 | 99 | 90 | 83 | 95 | 68 | 96 | 100 | 100 | — | 99 | 100 | 100 | — | — | — | — | 87 | — | — | — | 58 |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model