Search Intelligence Score
58.2
+35.6 lift from search
050100
- Lift from search
- +35.6
- 22.6 without search
- Cost per 1K tasks
- $28.4
- Below the median score of 61.9, so not ranked on cost
- Time per task
- 363s
- Search plus inference time to complete one task
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA76.5 vs 33.6
- HLE42.0 vs 26.0
- WISER56.0 vs 8.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $15.8
- 56%
- Search
- $5.29
- 19%
- Extract
- $7.30
- 26%
Compared with
Other models from the same provider alongside models that score closest.
- Hunyuan 358.2Cost $28.4 · Lift +35.6 · 363s
- DS Pro58.4Cost $110 · Lift +27.9 · 383s
- Gemini 358.6Cost $114 · Lift +24.5 · 276s
- DS Flash 073159.2Cost $13.6 · Lift +35.2 · 292s
- GPT-5.6 Luna60.7Cost $36.2 · Lift +33.9 · 98.0s
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Hunyuan 3 | 58.2 | +35.6 | $28.4 | 363s |
| DS ProDeepSeek V4 Pro | 58.4 | +27.9 | $110 | 383s |
| Gemini 3Gemini 3 Flash | 58.6 | +24.5 | $114 | 276s |
| DS Flash 0731DeepSeek V4 Flash (0731) | 59.2 | +35.2 | $13.6 | 292s |
| GPT-5.6 LunaGPT-5.6 Luna | 60.7 | +33.9 | $36.2 | 98.0s |
Search Intelligence Score averages accuracy on DSQA, HLE, and WISER with equal weight; cost and time are averaged the same way, with cost shown per 1,000 tasks. Latest update September 25, 2026. Full methodology.
# Hunyuan 3 · Search Capability Leaderboard
- Search Intelligence Score: 58.2 (#19 in Search Intelligence)
- Without search: 22.6 · Lift from search +35.6
- Cost per 1K tasks: $28.4 (below the median score of 61.9, so not ranked on cost)
- Time per task: 363s
- Lab: Tencent · Model id: tencent/hy3
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 76.5 | 33.6 |
| HLE | 42.0 | 26.0 |
| WISER | 56.0 | 8.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Hunyuan 3 | 58.2 | +35.6 | $28.4 | 363s |
| DeepSeek V4 Pro | 58.4 | +27.9 | $110 | 383s |
| Gemini 3 Flash | 58.6 | +24.5 | $114 | 276s |
| DeepSeek V4 Flash (0731) | 59.2 | +35.2 | $13.6 | 292s |
| GPT-5.6 Luna | 60.7 | +33.9 | $36.2 | 98.0s |
Latest update September 25, 2026. Methodology: /leaderboard#methodology