GPT-6-Astra solves 49 of 50 physics research problems at $2.40 apiece
- Who
- The benchmark authors
- What
- evaluated commercially available AI agents on 50 theoretical physics research problems
- Quote
The team tested commercially available AI agents and gave them no human hints.
What happened
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.
Why it matters
The benchmark distinguishes proficiency in concrete physics calculations from the ability to choose fruitful research questions, clarifying which parts of scientific work its high scores actually measure.
The story so far
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.
Keep reading
Latest daily · Issue 24NVIDIA and AI4Bharat Introduce Nemotron-pretraining-Indic-v1 and an Open Data Generation PipelineTrending now
- 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
- 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
- 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
- 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights
Tomorrow at 08:00, a briefing like this arrives in your inbox.
The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-17