Benchmark Almanac

Ring-1T

Ring-1T ranks first on CNMO 2024.

Ant Group Released October 10th, 2025 Family Ring 2.0 The lab's model card Compare with others
29
Benchmarks with a score
1
Ranked first, out of five or more models
5
In the top three
Ant Group Oct 2025

Ring-1T

Open weights Flagship

141.3 #167 of 404
Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.
  • BBEH micro average 59.6% #4 /15
  • HealthBench 57.9% #18 /31
  • PHYBench 42.6% #3 /5

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.

Knowledge and language

BenchmarkScoreRankSource
AGIEval 88.1% #3 of 40 Lab model card
Arena-Hard v2.0 81.6% #4 of 24 Lab model card
Creative Writing v3 85.4 #3 of 12 Lab model card
C-Eval 91.5% #12 of 46 Lab model card
BBEH micro average 59.6% #4 of 15 Lab model card
ConStory-Bench 0.54 #5 of 14 Official leaderboard
MMLU-Pro 80.5% #76 of 167 Lab model card
CMMLU 89.1% #8 of 17 Lab model card
TriviaQA 78.6% #21 of 40 Lab model card
IFEval 85.2% #79 of 135 Lab model card
MultiChallenge 50.9% #31 of 42 Lab model card
Humanity's Last Exam 16% #121 of 154 Lab model card

Math and science

BenchmarkScoreRankSource
CNMO 2024 88.5% #1 of 7 Lab model card
ZebraLogic 95.2% #4 of 23 Lab model card
AIME 2025 93.4% #30 of 143 Lab model card
Omni-MATH 82.6% #1 of 4 Lab model card
GPQA Diamond 78.6% #128 of 302 Lab model card
HMMT 2025 86.7% #28 of 54 Lab model card
PHYBench 42.6% #3 of 5 Lab model card
ARC-AGI 55.9% #16 of 21 Lab model card
UGMathBench 76.5% #1 of 1 Lab model card

Coding

BenchmarkScoreRankSource
Aider-Edit 78.6% #2 of 5 Lab model card
LiveCodeBench v6 78.3% #37 of 90 Lab model card
Codeforces rating 2,088 #21 of 47 Lab model card
ICPC World Finals 2025 5.00 #3 of 3 Lab model card

Agents and tools

BenchmarkScoreRankSource
Berkeley Function Calling Leaderboard (BFCL) 68.8% #21 of 41 Lab model card
SnakeBench 16 #168 of 188 Official leaderboard

Professional work

BenchmarkScoreRankSource
HealthBench 57.9% #18 of 31 Lab model card
FinanceReasoning 87.4% #1 of 1 Lab model card

Its lab's numbers put it at 141.3, number 167 of 404

The Self-Reported Index fits one score to the 18 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 138.7 to 143.9. How we compute it.

Its launch post

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

Its system card

Every result in the longer documents the lab published with it. 19 of them aren't in the launch post.

Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model Oct 21, 2025

Capabilities

Health