ObviousBenchGPQA.ai

Cost–score frontier

Compare exact Clean score with the Cost of one normalized 189-question pass.
Cheaper configurations appear farther right; the black line is the global Pareto reference.

Results 0.1.14Data through Oct 8, 2026

Display
252 of 268 plotted16 Cost unavailable6 DeepSeek configurations use off-peak pricing

GPQA Diamond Clean · Cost

Global Cost–score frontier

Filters highlight configurations without changing the global reference.

  • Color = manufacturer
  • Diamond = reasoning setting
  • Circle = none, minimal, or default
  • Black line = global Pareto reference

Loading verified Cost data…

Clean scores use exact numerators and denominators. Cost uses a logarithmic scale with cheaper configurations farther right.
Cost for 189 questions, one attempt eachPrices dated 2026-10-10Results 0.1.14 · source 2f99dac7c610

Table explorer

Loading verified configurations…

Accessible chart summary

Verified chart data is loading.

How Cost and the frontier are calculated

Each x-coordinate is the public API Cost for the configuration’s observed average tokens across 189 retained questions, normalized to one attempt per question. The y-coordinate is its exact Clean score. A point is on the global Pareto frontier when no configuration is both cheaper and at least as accurate, or equally priced and more accurate. Configurations with unavailable Cost are excluded rather than treated as zero.

The graph and table use DeepSeek’s off-peak prices. Both off-peak and peak prices remain available in the leaderboard and Cost download. Manufacturer, model, effort, protocol, focus, and near-ceiling controls only change presentation.