Benchmark
BIG-Bench
What is BIG-Bench?
Beyond the Imitation Game Benchmark (BIG-bench) is a collaborative benchmark consisting of 204+ tasks designed to probe large language models and extrapolate…
- Released
- 2022-06-09
- Modality
- text
- Evaluates
- math, reasoning, language
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 3
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/big-bench?top_n=500
BIG-Bench results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Gemini 1.0 Pro | 0.75 | 2024-02-15 | evidence | |
| Gemma 2 27B | 0.749 | 2024-06-27 | evidence | |
| Gemma 2 9B | 0.682 | 2024-06-27 | 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.