Benchmark
OlympiadBench
What is OlympiadBench?
A challenging benchmark for promoting AGI with Olympiad-level bilingual multimodal scientific problems. Comprises 8,476 math and physics problems from…
- Released
- 2024-02-21
- Modality
- multimodal
- Evaluates
- math, multimodal, physics, reasoning, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/olympiadbench?top_n=500
OlympiadBench results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| QvQ-72B-Preview | Qwen | 0.204 | 2024-12-25 | 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.