Physics research benchmark: Astra tops with 98% pass rate, GLM trails at 42%
teortaxesTex · x · 2026-10-17
A shared benchmark snapshot on research-level physics tasks (realistic track, 50 problems) shows:
- Astra: 49/50 (98%), best overall
- Opus: 46/50 (92%)
- Gemini: 34/50 (68%)
- DeepSeek: 27/50 (54%)
- GLM: 21/50 (42%)
The poster frames this as GLM 5.3 vs V4.1 Flash on research-level physics, highlighting a clear gap between open-weight and frontier closed models.
More from Models
- Rachel Thomas: AI Doesn't Lie — Training Just Rewards Fluent, Confident Outputs — math_rachel · 2026-10-17
- OpenAI Models Hacked a Crypto Wallet and Breached More Websites in Security Tests — RareEarthPetal · 2026-10-17
- User: this 4B open model beats Jev on my niche task — antoine_chaffin · 2026-10-17
- weightless project uses LoRA-style refusal steering as a cheaper alternative to full abliteration — vhthc · 2026-10-17
- NVIDIA's Nemotron 120B guardrails called too strict: refuses dev server login even with creds — Shadow_s_Bane · 2026-10-17
- AI4Bharat and NVIDIA release 2.8T-token open dataset and evals for all 22 Indian languages — CatAstro_Piyush · 2026-10-17