Ring-1T
Ring-1T ranks first on CNMO 2024.
28
Benchmarks with a score
1
Ranked first, out of five or more models
5
In the top three
Ant Group Oct 2025 Ring-1T
Open weights Flagship
No Epoch Capabilities Index score yet
- BIG-Bench Extra Hard 59.6% #4 /11
- HealthBench 57.9% #17 /30
- PHYBench 42.6% #3 /5
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
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AGIEval | 88.1% | #3 of 35 | Model card | |
| Arena-Hard v2.0 | 81.6% | #4 of 24 | Model card | |
| Creative Writing v3 | 85.4 | #3 of 12 | Model card | |
| C-Eval | 91.5% | #11 of 38 | Model card | |
| BIG-Bench Extra Hard | 59.6% | #4 of 11 | Model card | |
| CMMLU | 89.1% | #8 of 17 | Model card | |
| MMLU-Pro | 80.5% | #72 of 151 | Model card | |
| TriviaQA | 78.6% | #20 of 39 | Model card | |
| IFEval | 85.2% | #72 of 126 | Model card | |
| MultiChallenge | 50.9% | #28 of 36 | Model card | |
| Humanity's Last Exam | 16% | #115 of 147 | Model card |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CNMO 2024 | 88.5% | #1 of 6 | Model card | |
| ZebraLogic | 95.2% | #4 of 23 | Model card | |
| AIME 2025 | 93.4% | #30 of 143 | Model card | |
| Omni-MATH | 82.6% | #1 of 4 | Model card | |
| GPQA Diamond | 78.6% | #120 of 284 | Model card | |
| HMMT 2025 | 86.7% | #26 of 49 | Model card | |
| PHYBench | 42.6% | #3 of 5 | Model card | |
| ARC-AGI | 55.9% | #14 of 19 | Model card | |
| UGMathBench | 76.5% | #1 of 1 | Model card |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Aider-Edit | 78.6% | #2 of 5 | Model card | |
| LiveCodeBench v6 | 78.3% | #34 of 76 | Model card | |
| Codeforces rating | 2,088 | #21 of 41 | Model card | |
| ICPC World Finals 2025 | 5.00 | #3 of 3 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Berkeley Function Calling Leaderboard (BFCL) | 68.8% | #26 of 47 | Model card | |
| SnakeBench | 16 | #163 of 183 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HealthBench | 57.9% | #17 of 30 | Model card | |
| FinanceReasoning | 87.4% | #1 of 1 | 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. 19 of them aren't in the launch post.
Capabilities
- AIME 2025 93.4
- Omni-MATH 82.6
- HMMT 2025 86.7
- CNMO 2024 88.5
- FinanceReasoning 87.4
- UGMathBench 76.5
- LiveCodeBench v6 78.3
- Codeforces rating 2088
- Aider-Edit 78.6
- ARC-AGI 55.9
- BIG-Bench Extra Hard 59.6
- ZebraLogic 95.2
- Humanity's Last Exam 16
- GPQA Diamond 78.6
- MMLU-Pro 80.5
- C-Eval 91.5
- PHYBench 42.6
- AGIEval 88.1
- TriviaQA 78.6
- CMMLU 89.1
- Arena-Hard v2.0 81.6
- Creative Writing v3 85.4
- IFEval 85.2
- MultiChallenge 50.9
- Berkeley Function Calling Leaderboard (BFCL) 68.8
- IMO 2025
Health
- HealthBench 57.9