The best inclusionAI model for science is Ring-2.6-1T, scoring 85.7% on GPQA Diamond — graduate-level physics, chemistry and biology. Ling-2.6-1T (75.2%) and Ling-2.6-flash (59.3%) round out the top three.
AI models ranked by GPQA Diamond — graduate-level physics, chemistry and biology questions written to be un-Googleable, so the score reflects reasoning from knowledge rather than retrieval. The best large language models for scientific research and hard-science work.
The best inclusionAI model for science is Ring-2.6-1T, scoring 85.7% on GPQA Diamond — graduate-level physics, chemistry and biology. Ling-2.6-1T (75.2%) and Ling-2.6-flash (59.3%) round out the top three.
Ling-2.6-1T (75.2%) is the closest alternative on this metric, followed by Ling-2.6-flash (59.3%). See the full ranking above for the tradeoffs.
modelgrep tracks 4 inclusionAI models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Ring-2.6-1T. 3 of them qualify for this ranking.