Benchmark Almanac

Ling-2.6-1T

Ling-2.6-1T.

Ant Group Released 29 Apr 2026 Family Ling 2.6 The lab's model card
23
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Ant Group Apr 2026

Ling-2.6-1T

Open weights Flagship

No Epoch Capabilities Index score yet
  • IFBench 57.6% #54 /70
  • BFCL V4 70.6% #8 /24
  • LongBench v2 48.3% #23 /27

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
MRCR v2 80.4% #9 of 27 Model card
Chinese SimpleQA 76.5% #5 of 13 Model card
BIG-Bench Extra Hard 52.4% #5 of 11 Model card
SimpleQA Verified 31.5% #14 of 22 Model card
SuperGPQA 58.3% #18 of 26 Model card
IFBench 57.6% #54 of 70 Model card
LongBench v2 48.3% #23 of 27 Model card
Humanity's Last Exam 10.1% #136 of 147 Model card
Extended NYT Connections 4.10% #97 of 97 Official leaderboard

Math and science

BenchmarkScoreRankSource
GPQA Diamond 76.2% #133 of 284 Model card
HMMT Nov 2025 81.9% #20 of 23 Model card
AIME 2026 87.4% #30 of 34 Model card
ARC-AGI 50.9% #17 of 19 Model card
IMO-AnswerBench 65.8% #35 of 37 Model card

Coding

BenchmarkScoreRankSource
SWE-bench Verified 72.2% #62 of 150 Model card
LiveCodeBench v6 65.6% #59 of 76 Model card

Agents and tools

BenchmarkScoreRankSource
PinchBench 2.0 82.6% #13 of 57 Official leaderboard
BFCL V4 70.6% #8 of 24 Model card
SnakeBench 25 #82 of 183 Official leaderboard
tau2-bench 78.4% #40 of 69 Model card
PinchBench 87.4% #8 of 13 Model card
Terminal-Bench 2.0 40.5% #50 of 61 Model card
Claw-Eval Pass^3 51% #10 of 11 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. 12 of them aren't in the launch post.

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale 13 Jun 2026

Capabilities