Model
HY4 Preview
Tencent
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Doc2Harness | 38.9 | pass_rate | N/A | Independent | medium | arxiv.org |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| LifeSearch | 49.7 | score | N/A | Independent | medium | arxiv.org |
Instruction Following
Instruction Following| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Design Creativity Bench | 46.2 | overall | N/A | Independent | medium | arxiv.org |
Safety & Alignment
Safety & AlignmentReproduced by the community
Loading community runs…