Benchmark
BABE Benchmark
What is BABE?
Biology Arena BEnchmark; measures experimental reasoning and causal inference over peer-reviewed biological research papers.
- Evaluates
- reasoning
- Openness
- unknown
- Catalog source
- Model reports
- Reported scores
- 3
BABE paper
BABE results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Seed2.0 Lite | ByteDance | 50.2 | 2026-02-14 | evidence |
| Seed2.0 Mini | ByteDance | 40.4 | 2026-02-14 | evidence |
| Seed2.0 Pro | ByteDance | 50.0 | 2026-02-14 | 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.
Which sources cite BABE?
- Seed2.0 (Pro / Lite / Mini) ByteDance, 2026-02-14