Ring-2.5-1T

Ring-2.5-1T ranks first on HMMT Nov 2025.

Ant Group Released February 10th, 2026 Family Ring 2.5 The lab's model card Compare with others

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Ant Group Feb 2026

Ring-2.5-1T

Open weights Flagship

144.8 #135 of 404

Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.

tau2-bench 78.4% #44 /79
LiveCodeBench v6 89.4% #8 /90
IMO-AnswerBench 90% #2 /37

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Math and science

Benchmark	Score	Rank	Source
HMMT Nov 2025	98.3%	#1 of 28	Lab model card
IMO-AnswerBench	90%	#2 of 37	Lab model card
AIME 2026	95%	#13 of 38	Lab model card
CMO 2025	105.0	#2 of 3	Lab model card
ARC-AGI-2	19.3%	#22 of 24	Lab model card

Coding

Benchmark	Score		Rank	Source
LiveCodeBench v6	89.4%		#8 of 90	Lab model card
SWE-bench Verified	72.4%		#61 of 155	Lab model card

Agents and tools

Benchmark	Score		Rank	Source
tau2-bench	78.4%		#44 of 79	Lab model card
Meta Agents Research Environments (ARE) / Gaia2	75%		#2 of 3	Lab model card

Its lab's numbers put it at 144.8, number 135 of 404

The Self-Reported Index fits one score to the 7 capability results Ant Group reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 140.5 to 149.0. How we compute it.

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Ring-2.5-1T model card (Hugging Face) Feb 10, 2026