Llama-4-Maverick-17B-128E-Instruct-FP8
45±1
42interval46
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 43 min43 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· 43 minutes ago
- SWE-bench· 43 minutes ago
- Terminal-Bench· 43 minutes ago
- ARC-AGI-2· 43 minutes ago
Filter by org:
Released:
llama-4-maverick-17b-128e-instruct
36±1
35interval37
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 | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 584 | 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 | #233–584 | — | — | — | — | — | — | — | 49 | 29 | 12 | — | — | — | — | — | 56 | — | — | — | — | — | 63 | ||
| 924 | llama-4-maverick-17b-128e-instruct | meta | Apr 2025 | $0.19 / $0.65 | 36.4 29.5Ranked 36.4 = (6 × 29.5 + 3 × 50) ÷ 9. 29.5 is the mean percentile over the 6 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 35–37 | 41 | 6/22 | #199–924 | 42 | — | 30 | — | — | — | — | — | — | — | — | 11 | 20 | 22 | 52 | — | — | — | — | — | — | — |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model