GDPval-AA v2.1
A bird's-eye view of the benchmark: what it measures and every AI IQ chart built on it.
| # | Model | Effort | Score | Effective cost (est.) | Completion time (est.) | Weights |
|---|
About GDPval-AA v2.1
What GDPval-AA v2.1 measures
GDPval-AA v2.1 does not yet have two source-matched reasoning-effort score/cost rows for one model, so the Cost Efficiency chart shows one point per model and will connect effort levels when qualifying data is imported.
Reading the cost view
GDPval-AA v2.1 publishes no per-run cost, so this chart falls back to each model's estimated effective cost per 1M I/O tokens (a runtime estimate from measured or imputed token usage, not a published task cost). Explicit reasoning/nonreasoning siblings are connected where both are public; every other model is a standalone point. Up and to the left is better.
Reading the completion-time view
Each point is a public model's GDPval-AA v2.1 score against its estimated completion time (time to last token) for the input and output lengths set by the sliders. Timing comes from the site's per-model speed measurements, not from the benchmark run, so every point is an estimate and labels carry a ~ prefix. The newest generation with a published result is shown by default. Up and to the left is better.
Reading the score bars
Bars rank models by the source-backed benchmark value used for this chart. Longer bars indicate higher published scores.
Reading the model table
Each row is one canonical model: the score shown is the same best published configuration the score bars use. Models with several published reasoning-effort levels expand to one sub-row per level, with the score and effective cost per 1M I/O Tokens the source reports for that level. This benchmark publishes no per-run cost, so the cost column is the site's estimated effective cost per 1M I/O tokens (marked ~). Completion time is the site's estimated time to last token for a 10K-token input and 1K-token output (marked ~), not a benchmark run time. The top 20 rows are shown by default; click a column heading to sort, and missing values always sort last.