Benchmark Almanac

Ring-2.6-1T

Ring-2.6-1T.

Ant Group Released May 14th, 2026 Compare with others
15
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Ant Group May 2026

Ring-2.6-1T

Open weights

153.4 #72 of 404
Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.
  • Claw-Eval Pass^3 63.8% #4 /13
  • ClawProBench 62% #15 /49
  • tau2-bench 95.3% #6 /79

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

BenchmarkScoreRankSource
GPQA Diamond 88.3% #50 of 302 Lab model card
AIME 2026 95.8% #7 of 38 Lab model card
IMO-AnswerBench 86.1% #10 of 37 Lab model card
HMMT 2026 93.5% #7 of 19 Lab model card
ARC-AGI-2 66.2% #11 of 24 Lab model card

Coding

BenchmarkScoreRankSource
LiveCodeBench v6 87% #16 of 90 Lab model card
SWE-bench Verified 74% #53 of 155 Lab model card
SWE-Bench Pro 53.8% #57 of 81 Lab model card

Agents and tools

BenchmarkScoreRankSource
tau2-bench 95.3% #6 of 79 Lab model card
ClawProBench 62% #15 of 49 Official leaderboard
Claw-Eval Pass^3 63.8% #4 of 13 Lab model card
Meta Agents Research Environments (ARE) / Gaia2 77.9% #1 of 3 Lab model card
PinchBench 87.6% #7 of 14 Lab model card
SnakeBench 23 #108 of 188 Official leaderboard
Claw-Eval 63.8% #10 of 13 Lab model card

Its lab's numbers put it at 153.4, number 72 of 404

The Self-Reported Index fits one score to the 12 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 150.3 to 156.5. 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. 7 of them aren't in the launch post.