AI Agents Solve Most Problems in Theoretical Physics Benchmark

1 reports 1 reporting sources 2 days agoNew

Understand the event

AI overview

GPT-6-Astra solved 49 of 50 TheoPhysEval theoretical physics problems while running in OpenAI’s Codex environment without human hints, at a total cost of just under $116. The benchmark spans eleven theoretical physics subfields. Anthropic’s Opus 5.5 scored 92 percent; with internet access disabled, both models scored 92 percent. The researchers emphasized that TheoPhysEval tests calculations using known methods. Choosing promising research questions remains a separate challenge for current agents, so the results demonstrate performance on those calculations rather than the full process of theoretical physics research.

Generated by AI from reports · Updated 2 days ago

Latest development10/15 23:24 (UTC+8)

GPT-6-Astra solves 49 of 50 physics research problems at $2.40 apiece The Decoder

Report timeline

Follow the reports to explore different sides of the event.

10/15

23:24
The DecoderPicks
GPT-6-Astra solves 49 of 50 physics research problems at $2.40 apiece
GPT-6-Astra, running in OpenAI's Codex environment without human hints, solved 49 of 50 TheoPhysEval problems across eleven theoretical physics subfields, costing just under $116 overall. Anthropic's Opus 5.5 scored 92 percent, while both models reached 92 percent without internet access. The researchers emphasize that the benchmark tests calculations using known methods, while choosing promising research questions remains a separate challenge for current agents.

Event heat trend

可比范围当前: 4
Peak within comparable coverage: 1010/16 00:00 (UTC+8)
近 24 小时变化: -50%

Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.

Keep reading

Latest daily · Issue 24NVIDIA and AI4Bharat Introduce Nemotron-pretraining-Indic-v1 and an Open Data Generation Pipeline