Scientific Reasoning

A bird's-eye view of the dimension: the main IQ chart, the effective-cost frontier, and the benchmark charts that feed it.

Scientific Reasoning IQ
Each model's Scientific Reasoning IQ plotted on a standard normal IQ distribution
Controls:

How to read this chart

Models are placed on a standard IQ-style distribution using Scientific Reasoning IQ. Higher scores appear farther to the right.

Benchmarks in this dimension

Scientific Reasoning vs Effective Cost
X = effective cost (log). Y = Scientific Reasoning IQ. Color = provider.
Controls:
Science1:1Cost

How to read this chart

Each point is a public model. The chart compares Scientific Reasoning IQ against Effective Cost (per 1M I/O Tokens), with color showing the model provider.

Humanity's Last Exam Benchmark Scores
Each model's Humanity's Last Exam score. Color = provider.
Controls:

How to read this chart

Bars rank models by the source-backed benchmark value used for this chart. Longer bars indicate higher published scores.

GPQA Diamond Benchmark Scores
Each model's GPQA Diamond score. Color = provider.
Controls:

How to read this chart

Bars rank models by the source-backed benchmark value used for this chart. Longer bars indicate higher published scores.

SciCode Benchmark Scores
Each model's SciCode score. Color = provider.
Controls:

How to read this chart

Bars rank models by the source-backed benchmark value used for this chart. Longer bars indicate higher published scores.

CritPt Benchmark Scores
Each model's CritPt percentage score. Color = provider.
Controls:

How to read this chart

Bars rank models by the source-backed benchmark value used for this chart. Longer bars indicate higher published scores.