- IMO-AnswerBench 73.4
- HMMT2025 85.8
- HLE 18.8
- ARC AGI_1 52.9
- Multi Challenge 62.6
- Terminal Bench 34.6
- SWE-bench Verified 53
- Tau2-Bench 72.4
Tencent HY 2.0 Think
Tencent HY 2.0 Think.
10
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Tencent Dec 2025 Tencent HY 2.0 Think
Closed weights Flagship
138.2
#192 of 404
Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.
- CL-bench 17.2% #15 /24
- CL-bench Life 8.40% #14 /16
- tau2-bench 72.4% #53 /79
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 | |
|---|---|---|---|---|
| MultiChallenge | 62.6% | #15 of 42 | Lab model card | |
| CL-bench | 17.2% | #15 of 24 | Official leaderboard | |
| Humanity's Last Exam | 18.8% | #109 of 154 | Lab model card | |
| CL-bench Life | 8.40% | #14 of 16 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HMMT 2025 | 85.8% | #29 of 54 | Lab model card | |
| ARC-AGI | 52.9% | #18 of 21 | Lab model card | |
| IMO-AnswerBench | 73.4% | #34 of 37 | Lab model card |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SWE-bench Verified | 53% | #125 of 155 | Lab model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| tau2-bench | 72.4% | #53 of 79 | Lab model card | |
| Terminal-Bench | 34.6% | #17 of 22 | Lab model card |
Its lab's numbers put it at 138.2, number 192 of 404
The Self-Reported Index fits one score to the 8 capability results Tencent reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 135.6 to 140.9. How we compute it.
- HMMT 2025 85.8
- IMO-AnswerBench 73.4
- tau2-bench 72.4
- MultiChallenge 62.6
- SWE-bench Verified 53
- ARC-AGI 52.9
- Terminal-Bench 34.6
- Humanity's Last Exam 18.8
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.