Search Capability Leaderboard
Hy4
TencentOpen weights
Evaluated
3Bronze / Search Intelligence3Bronze / Search Efficiency
Search Intelligence Score
75.4
+45.3 lift from search
050100
- Lift from search
- +45.3
- 30.2 without search
- Cost per 1K tasks
- $94.4
- #3 in Search Efficiency
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA90.3 vs 44.5
- HLE58.0 vs 36.0
- WISER78.0 vs 10.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $68.8
- 73%
- Search
- $7.27
- 8%
- Extract
- $18.3
- 19%
Compared with
Other models from the same provider alongside models that score closest.
- Hy475.4Cost $94.4 / Lift +45.3
- Hy4 Preview64.6Cost $93.2 / Lift +33.9
- Hunyuan 358.2Cost $28.4 / Lift +35.6
- Opus 5.576.1Cost $896 / Lift +31.9
- Gemini 4 Carbon74.2Cost $472 / Lift +33.6
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| Hy4 | 75.4 | +45.3 | $94.4 |
| Hy4 PreviewHy4 Preview | 64.6 | +33.9 | $93.2 |
| Hunyuan 3Hunyuan 3 | 58.2 | +35.6 | $28.4 |
| Opus 5.5Claude Opus 5.5 | 76.1 | +31.9 | $896 |
| Gemini 4 CarbonGemini 4 Carbon | 74.2 | +33.6 | $472 |
Search Intelligence Score averages accuracy on DSQA, HLE, and WISER with equal weight; cost is averaged the same way, with cost shown per 1,000 tasks. Evaluated . Leaderboard last updated . Full methodology.
# Hy4 / Search Capability Leaderboard
- Search Intelligence Score: 75.4 (#3 in Search Intelligence)
- Without search: 30.2 / Lift from search +45.3
- Cost per 1K tasks: $94.4 (#3 in Search Efficiency)
- Medals: Bronze, Search Intelligence; Bronze, Search Efficiency
- Evaluated:
- Lab: Tencent / Weights: Open weights / Model id: tencent/hy4
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 90.3 | 44.5 |
| HLE | 58.0 | 36.0 |
| WISER | 78.0 | 10.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| Hy4 | 75.4 | +45.3 | $94.4 |
| Hy4 Preview | 64.6 | +33.9 | $93.2 |
| Hunyuan 3 | 58.2 | +35.6 | $28.4 |
| Claude Opus 5.5 | 76.1 | +31.9 | $896 |
| Gemini 4 Carbon | 74.2 | +33.6 | $472 |
Leaderboard last updated . Methodology: /leaderboard#methodology