Benchmark
GAIA2 Benchmark
What is GAIA2?
GAIA2 evaluates general-purpose AI agents on real-world, multi-step questions that require reasoning, tool use, and information retrieval.
- Modality
- multimodal
- Evaluates
- reasoning, general, agents, tool calling
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/gaia2?top_n=500
GAIA2 results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Muse Glimmer-30B | Meta | 0.433 | 2026-08-10 | 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.