Search Capability Leaderboard
Claude Sonnet 5
Anthropic
#11 in Search Intelligence · #9 in Search Efficiency
Search Intelligence Score
53.7
+33.3 lift from search
050100
- Lift from search
- +33.3
- 20.3 without search
- Cost per 1K tasks
- $223
- #9 in Search Efficiency
- Time per task
- 83.3s
- Search plus inference time to complete one task
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA48.0 vs 9.0
- HLE46.0 vs 40.0
- WISER67.0 vs 12.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $215
- 96%
- Search
- $2.89
- 1%
- Extract
- $4.98
- 2%
InferenceSearchExtract
Compared with
Other models from the same provider alongside models that score closest.
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Claude Sonnet 5 | 53.7 | +33.3 | $223 | 83.3s |
| Opus 5Claude Opus 5 | 59.3 | +25.3 | $235 | 74.5s |
| Fable 5.1Claude Fable 5.1 | 61.0 | +29.1 | $455 | 81.5s |
| Gemini 3.7Gemini 3.7 Flash | 54.3 | +25.3 | $61.1 | 79.7s |
| GPT-5.6 LunaGPT-5.6 Luna | 54.7 | +32.3 | $23.0 | 59.4s |
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 14, 2026. Full methodology.
# Claude Sonnet 5 · Search Capability Leaderboard
- Search Intelligence Score: 53.7 (#11 in Search Intelligence)
- Without search: 20.3 · Lift from search +33.3
- Cost per 1K tasks: $223 (#9 in Search Efficiency)
- Time per task: 83.3s
- Lab: Anthropic · Model id: claude-sonnet-5
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 48.0 | 9.0 |
| HLE | 46.0 | 40.0 |
| WISER | 67.0 | 12.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Claude Sonnet 5 | 53.7 | +33.3 | $223 | 83.3s |
| Claude Opus 5 | 59.3 | +25.3 | $235 | 74.5s |
| Claude Fable 5.1 | 61.0 | +29.1 | $455 | 81.5s |
| Gemini 3.7 Flash | 54.3 | +25.3 | $61.1 | 79.7s |
| GPT-5.6 Luna | 54.7 | +32.3 | $23.0 | 59.4s |
Latest update September 14, 2026. Methodology: /leaderboard#methodology