Reported in recent model launches

These model reports include this benchmark. Their harnesses, task subsets, scoring policies, and resource budgets can differ; follow each report’s evaluation notes before joining the numbers.

OpenAI · GPT-6 Astra →Kimi · Kimi K2.6 · earlier-2026 baseline →

What it measures

A demanding subset of expert-written science questions tests detailed reasoning in specialist domains.

How to read the result

A compact diagnostic for scientific question answering, especially when analyzed by error type and subject.

Limits and comparison traps

Small samples and multiple-choice guessing can move rankings. Repeated attempts are not the same measurement as one attempt.

Epoch data and evaluation setting

Epoch AI publishes this benchmark in its capability collection. Imported rows retain the published score column and model configuration. Original authors and evaluation providers remain credited in the result references.

Epoch attribution and score coverage

Data is attributed to Epoch AI under CC BY 4.0, with original evaluation providers credited in the linked source snapshots. Scores are imported only where a published mapping identifies the field and its scale; missing or incompatible records are omitted rather than assigned zero.

Published evaluation

The linked publication documents the task and scoring procedure. Model results retain the source’s evaluation setting, native score units and available uncertainty.

Published evaluation

Exact values from the publisher’s embedded full comparison table. Maximum effort, fallback settings and dated model versions remain in model labels. Blank cells stay missing. Source footnotes specify mixed harnesses and externally quoted comparisons; this is a launch-reported cohort rather than a new independent evaluation.

Where this fits in an evaluation suite

A correct multiple-choice answer and a supported scientific contribution demand different evidence. Check whether the score rewards a proposal, an executed experiment, or a completed research target.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

Exact values from the publisher’s embedded full comparison table. Maximum effort, fallback settings and dated model versions remain in model labels. Blank cells stay missing. Source footnotes specify mixed harnesses and externally quoted comparisons; this is a launch-reported cohort rather than a new independent evaluation.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.

PRIMARY EVIDENCE & FURTHER READING

  1. Introducing Kimi K3.1 Pro ↗

    Moonshot AI · 2026

  2. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

  3. GPQA Diamond Benchmark | Artificial Analysis ↗

    Artificial Analysis

  4. GPQA Diamond ↗

    Epoch AI

  5. Capabilities & benchmarking — retained external evaluation records ↗

    Epoch AI · 2026

Reviewed 2026-10-27. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.