Ant Group
7 models 5 model cards read
What benchmarks does Ant Group mention most?
Here are the 6 benchmarks Ant Group mentions most in its launch posts.
Source: Labs’ launch posts, read by Benchmark Almanac
Source: Labs’ system cards and technical reports, read by Benchmark Almanac
LiveCodeBench v6 ARC-AGI AIME 2025 Codeforces rating Arena-Hard v2.0 HMMT 2025 HealthBench Creative Writing v3 GPQA Diamond Humanity's Last Exam BBEH micro average MultiChallenge IMO 2025 AIME 2026 tau2-bench SWE-bench Verified IMO-AnswerBench ARC-AGI-2 HMMT Nov 2025 Meta Agents Research Environments (ARE) / Gaia2 PinchBench Claw-Eval Pass^3 BFCL V4 IFBench MRCR v2 SWE-Bench Pro
Source: Labs’ launch posts, system cards and technical reports, read by Benchmark Almanac
Model cards
| Date | Model | Document | Benchmarks |
|---|---|---|---|
| Oct 13, 2026 | Ling-3.1-flash | Ling-3.1-flash model card (Hugging Face) | 23 |
| May 14, 2026 | Ring-2.6-1T | Ring-2.6-1T model card (Hugging Face) | 6 |
| Apr 29, 2026 | Ling-2.6-1T | Ling-2.6-1T model card (Hugging Face) | 8 |
| Feb 10, 2026 | Ring-2.5-1T | Ring-2.5-1T model card (Hugging Face) | 10 |
| Oct 10, 2025 | Ring-1T | Ring-1T: Flow State Leads to Sudden Enlightenment (Hugging Face model card) | 9 |
Every Ant Group model
- Ling-3.1-flash Oct 2026
- Ling-3.0-flash-Fin Sep 2026
- Ling-3.0-flash Aug 2026
- Ring-2.6-1T May 2026
- Ling-2.6-1T Apr 2026
- Ring-2.5-1T Feb 2026
- Ring-1T Oct 2025