AG
Ant Group
Language model · China ·Oct 2025

Ling-1T

Language Open (Restricted)
1T
Parameters
25
Benchmarks

About Ling-1T

Ling-1T is an AI model developed by Ant Group, in the language category, released in 2025, made available as an open-weights model with 1000B params.

On this page you'll find Ling-1T's full specifications, including 25 benchmark results. Review provider pricing and benchmark scores below, or compare Ling-1T head-to-head with other language models.

Links

Run Ling-1T locally — what it takes

Ling-1T (1,000B) is too large to run on a single consumer or Apple machine. At Q4 its weights alone are about 560 GB — it needs a multi-GPU / datacenter setup:

  • ≈ 3× AMD Instinct MI325X
  • ≈ 4× NVIDIA B200

Lower quantization (Q3/Q2) or CPU + system-RAM offload (e.g. ktransformers) reduces the requirement at the cost of speed.

Software support

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Community

Would you run Ling-1T again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Ling-1T benchmark scores
Benchmark Category Score Variant
Codeforces Elo code 1,901 rating
FullStackBench code 56.55% pass@1
LiveCodeBench code 61.68% pass@1
MBPP code 96.87% sanitized-pass@1
Aider Benchmark coding 83.65 edit-acc
MultiPL-E coding 77.91 pass@1
ArenaHard v2 general 75.83 win-rate
C-Eval general 92.19%
IFEval general 86.11% prompt-strict
MMLU-Pro general 82.04%
MMLU-Redux general 92.25%
MultiChallenge general 58.24%
AIME 2024 math 80.21% pass@1
AIME 2025 math 70.42% pass@1
CNMO 2024 math 79.25% pass@1
HMMT February 2025 math 47.08% pass@1
Omni-MATH math 74.46
UGMathBench math 74.95
ARC-AGI-1 reasoning 43.81 pass@1
BBEH reasoning 47.34
FinanceReasoning reasoning 87.45
GPQA Diamond reasoning 72.98% pass@1
Humanity's Last Exam reasoning 7.6% pass@1
ZebraLogic reasoning 90.8% pass@1
BFCL v3 tool-use 69.64% function-call

More models like Ling-1T

Frequently asked questions

What is Ling-1T?

Ling-1T is an AI model developed by Ant Group, in the language category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Ling-1T?

Ling-1T was developed by Ant Group and released in 2025.

Is Ling-1T open source or proprietary?

Ling-1T ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does Ling-1T cost?

Pricing for Ling-1T depends on the provider. See the providers table on this page for the latest API rates.

How does Ling-1T perform on benchmarks?

Ling-1T is benchmarked across 25 evaluations on GenAIList, including Codeforces Elo (1,901). See the full benchmark table below and compare it with other models.

Ling-1T, Ant Group's new flagship LLM
🤖 SC AI TECH NEWS | Ant Group launches “Ling-1T” — A Trillion-Parameter AI Model That’s 10× Faster!⚡
Ling 1T Model: Too Good to Be True?
Ant Group Unveils Ling-1T: A Trillion-Parameter AI Model Redefining Logical Reasoning and Innovation
Microsoft MAI Image 1 vs Google S2R vs Ant Group Ling 1T | The Global AI Revolution Explained

Know a great video about Ling-1T?