PCFBench - Total Emissions (Direct): leaderboard
Metric: Within-2x rate (%; share of 175 EPD products whose directly predicted total kgCO2e is within a factor of two of the declared total; from PCFBench, a product-carbon-footprint benchmark of 614 expert-labelled items; scored deterministically or by a temperature-0 judge; higher is better). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 77 |
| 2 | GPT-5.5 | 77 |
| 3 | Claude Opus 4.6 | 73 |
| 4 | Gemini 3 Flash | 73 |
| 5 | Claude Sonnet 4.6 | 63 |
| 6 | Claude Haiku 4.5 | 63 |
| 7 | DeepSeek V3.2 | 63 |
| 8 | GPT-5.4 Mini | 60 |
Interactive version: theaggregate.ai/benchmark?slug=pcfbench-total-emissions-direct · How It Works · Data refreshed daily, snapshot 2026-09-26.