Benchmark
GPQA (full) Benchmark
What is GPQA (full)?
The full split, distinct from the Diamond subset most frontier cards report. Benchmark Radar tracks 1 reported scores for GPQA (full), cited by 3 source…
- Released
- 2023-11-20
- Evaluates
- science
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 1
Source provenance
- Original evidence https://arxiv.org/abs/2311.12022
GPQA (full) paper
GPQA (full) results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen3.5-397B-A17B | Qwen | 88.4 | 2026-02-16 | 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 GPQA (full)?
- Qwen3.5-397B-A17B Qwen, 2026-02-16
- Olmo 3 (7B and 32B) Ai2, 2025-11-20
- Llama 3.1 405B Meta, 2024-07-23