Critical Physics Tasks

An Artificial Analysis metric for research-level physics reasoning.

ModelsModels with a result.180
Top resultBest result on this test.32.3%GPT-5.6 Sol
Top-3 spreadPoints from first to third.0.6 pts
YearYear of release.2026

Result and price

020406080100$0.03$0.1$0.3$1$3$10$30$100$300RESULTOUTPUT PRICE PER 1M TOKENS · LOG SCALE

Results

180 results
#ModelResultThe score from the source.
04GPT-6 Sol30.9%
11GPT-5.527.1%
15Kimi K323.4%
15GPT-5.423.4%
17GLM-5.220.9%
21GPT-6 Luna19.4%
22GLM-5.319.1%
25Grok 4.717.7%
29Grok 4.617.1%
34Grok 4.515.4%
42GPT-5.211.6%
43Muse Spark11.3%
52A.X K28.9%
55Grok 4.38.0%
60Inkling5.4%
64Hy34.9%
64GPT-5.14.9%
67GLM-5.14.6%
85GLM-52.0%
85Grok 42.0%
89GLM-4.71.7%
97o31.1%
117o10.3%
129Qwen3 Max0.0%
129Kimi K20.0%
129GLM-4.60.0%
129GPT-4.10.0%
129GPT-4o0.0%
129Nova Pro0.0%
129Phi-40.0%