Llama-4-Maverick-17B-128E-Instruct-FP8
45±1
42interval46
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 18 min18 minutes ago
All sources syncing normally
- Arena · Text· 7 hours ago
- Arena · WebDev· 7 hours ago
- Arena · Vision· 7 hours ago
- Arena · Agent· 7 hours ago
- GPQA Diamond· 18 minutes ago
- SWE-bench· 18 minutes ago
- Terminal-Bench· 18 minutes ago
- ARC-AGI-2· 18 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 | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 586 | Llama-4-Maverick-17B-128E-Instruct-FP8 | Meta AI | — | — | 44.8 41.7Ranked 44.8 = (5 × 41.7 + 3 × 50) ÷ 8. 41.7 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 42–46 | 51 | 5/22 | #233–586 | — | — | — | — | — | — | — | 49 | 29 | 12 | — | — | — | — | — | 56 | — | — | — | — | — | 63 |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model