Benchmark Almanac

Ring-2.6-1T

Ring-2.6-1T places in the top three on Claw-Eval Pass^3.

Ant Group Released 14 May 2026
16
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Ant Group May 2026

Ring-2.6-1T

Open weights

No Epoch Capabilities Index score yet
  • CritPt 3.71% #74 /160
  • tau2-bench 95.3% #6 /69
  • LiveCodeBench v6 87% #16 /76

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% #46 of 284 Model card
AIME 2026 95.8% #7 of 34 Model card
IMO-AnswerBench 86.1% #10 of 37 Model card
HMMT 2026 93.5% #6 of 18 Model card
ARC-AGI-2 66.2% #9 of 22 Model card
CritPt 3.71% #74 of 160 Epoch AI

Coding

BenchmarkScoreRankSource
LiveCodeBench v6 87% #16 of 76 Model card
SWE-bench Verified 74% #52 of 150 Model card
SWE-Bench Pro 53.8% #54 of 77 Model card
ALE-Bench 433 #103 of 121 Epoch AI

Agents and tools

BenchmarkScoreRankSource
tau2-bench 95.3% #6 of 69 Model card
Claw-Eval Pass^3 63.8% #3 of 11 Model card
Meta Agents Research Environments (ARE) / Gaia2 77.9% #1 of 3 Model card
PinchBench 87.6% #7 of 13 Model card
SnakeBench 23 #103 of 183 Official leaderboard
Claw-Eval 63.8% #9 of 14 Model card

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.