Benchmark
FigQA
FigQA is a multiple-choice benchmark on interpreting scientific figures from biology papers. It evaluates dual-use biological knowledge and multimodal…
- Modality
- multimodal
- Categories
- safety, healthcare, vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 3
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Claude Mythos Preview | Anthropic | 0.89 | 2026-04-07 | evidence |
| Claude Opus 4.6 | Anthropic | 0.783 | 2026-02-05 | evidence |
| Grok-4.1 Thinking | xAI | 0.34 | 2025-11-17 | 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.