GPQA Main ↗28.7%
GPT-4 with search · GPQA Main · Accuracy · original baselines ↗
OpenAI / MODEL EVIDENCE
GPT-4 with search
1 benchmarks · 1 observations · 1 sources
Scores at a glance
1 benchmarks · large dot: GPT-4 with search; small dots: closest models where reported
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
1 of 1 shared benchmark comparisons
1 of 1 shared benchmark comparisons
1 of 1 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark — published result table ↗
All 8 authors
Rein, David, Hou, Betty Li, Stickland, Asa Cooper, Petty, Jackson, Pang, Richard Yuanzhe, Dirani, Julien, Michael, Julian, Bowman, Samuel R.
Names used in source tables
GPT-4 with search