gemma-4-31b
58±3
55interval61
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 1 h1 hour ago
All sources syncing normally
- Arena · Text· 3 hours ago
- Arena · WebDev· 3 hours ago
- Arena · Vision· 3 hours ago
- Arena · Agent· 3 hours ago
- GPQA Diamond· 1 hour ago
- SWE-bench· 1 hour ago
- Terminal-Bench· 1 hour ago
- ARC-AGI-2· 1 hour ago
Filter by org:
Released:
gemma-4-31b-it
50±1
48interval51
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 | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 194 | gemma-4-31b | Mar 2026 | — | 58.1 62.2Ranked 58.1 = (6 × 62.2 + 3 × 50) ÷ 9. 62.2 is the mean percentile over the 6 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 55–61 | 66 | 6/22 | #63–214 | 83 | 30 | 76 | 65 | — | 26 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 92 | — | |||
| 424 | gemma-4-31b-it | Google DeepMind | Mar 2026 | $0.20 / $0.40 | 49.6 49.3Ranked 49.6 = (5 × 49.3 + 3 × 50) ÷ 8. 49.3 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 48–51 | 64 | 5/22 | #187–424 | — | — | — | — | — | — | — | 56 | 55 | — | 4 | — | — | — | 65 | — | — | — | — | — | — | 68 |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model