Benchmark
BIG-Bench Extra Hard
Successor to BBH after saturation; per-task variance is high.
- Released
- 2025-02-26
- Categories
- reasoning
- Openness
- unknown
- Source
- model_reports
- Reported scores
- 1
Reported scores
model_reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Gemma 4 (31B) | 74.4 | 2026-03-11 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.