The measurement
Each dot is one model's GPQA Diamond accuracy, plotted on its release date. Nothing on this chart is a forecast.
- Doubling
- ~6.7 mo
- 204 days · all measurements
- Fit
- r² 0.95
- 18 of 18 measurements fitted
- Measured span
- 35.7% 94.8%
- Mar 2023 → Aug 2026
How to read this chart
The axis is a log-odds scale, the same one the trend is fit on. Equal distance means an equal cut in the remaining error, so 50% to 90% is about the same step as 90% to 99%, which is why the labels crowd near the top. A percentage axis would flatten near 100% whether or not capability flattened. Very close to the ceiling the steps shorten, because a 198-question test cannot resolve past its own last item.
Our fit over all measurements doubles every 204 days. Epoch AI · Benchmarking Hub publish the scores and the release dates. The trend line through them is ours, and it is the only thing on this chart that is.
Measurements
18 modelsEvery point on the chart above, named. The date is the model's release, which is what the trend is regressed on.
| Model | Released | Position on the measured range | GPQA Diamond |
|---|---|---|---|
| Gemini 3.7 Flash | Aug 2026 | 94.8% | |
| GPT-5.4 Pro | Mar 2026 | 94.6% | |
| Gemini 3.1 Pro | Feb 2026 | 94.4% | |
| Gemini 3 Pro | Nov 2025 | 92.6% | |
| GPT-5.1 | Nov 2025 | 87.6% | |
| Grok 4 | Jul 2025 | 87.0% | |
| Gemini 2.5 Pro (Jun 2025) | Jun 2025 | 85.3% | |
| Gemini 2.5 Pro (Jun 2025) | Jun 2025 | 84.8% |
Questions
GPQA is answered by the same frontier language models Epoch's training-run series describes, so the systems measured and the systems setting the compute frontier are the same class. The reading is close to its ceiling: domain experts score about 65% and the frontier is at 94.8%, so this domain's date is as much about when the exam is exhausted as about capability, and the page says so.
No acceleration split has been justified for this series: GPQA's SOTA points sit on one line from GPT-4 onward, with no residual pattern of the kind that forced software's 2023 cut. Every SOTA measurement is fit, and this note says so.
No. Each domain is measured on its own scale - a task length in hours, an accuracy on a fixed test set - and every one of them scores a model on a bounded, pre-specified set of tasks. That is a measure of DEPTH on that set, not of breadth of competence. Depth is not breadth: a model can clear the bar on GPQA Diamond and still fail at things a child does.