GPQA Diamond ↗42.27%
GPT-4 Turbo Preview (January 2024) · GPQA diamond · Best score (across scorers) · % ↗
OpenAI / MODEL EVIDENCE
GPT-4 Turbo Preview (January 2024)
3 benchmarks · 4 observations · 3 sources · released 2024-01-25
Scores at a glance
3 benchmarks · large dot: GPT-4 Turbo Preview (January 2024); small dots: closest models where reported
MATH Level 5 ↗35.41%
GPT-4 Turbo Preview (January 2024) · MATH level 5 · Best score (across scorers) · % ↗
GPT-4 Turbo Preview (January 2024) · METR task performance & time horizons · Average task accuracy ↗
1 more reported result
5.36606 minutes · GPT-4 Turbo Preview (January 2024) · METR task performance & time horizons · 50% success task horizon · Epoch AI · METR Autonomy / Task-Horizon Suite · public result data ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Qwen2-72B →Qwen
3 of 3 shared benchmark comparisons
Claude 3 Opus →Anthropic
3 of 3 shared benchmark comparisons
3 of 3 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.
Names used in source tables
GPT-4 Turbo Preview (January 2024)