Search Capability Leaderboard
Claude Sonnet 5
Anthropic
#8 in Search Intelligence · #11 in Search Efficiency
Search Intelligence Score
66.6
+43.8 lift from search
050100
- Lift from search
- +43.8
- 22.8 without search
- Cost per 1K tasks
- $688
- #11 in Search Efficiency
- Time per task
- 846s
- Search plus inference time to complete one task
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA82.8 vs 32.5
- HLE45.0 vs 25.0
- WISER72.0 vs 11.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $673
- 98%
- Search
- $4.27
- 1%
- Extract
- $10.8
- 2%
Compared with
Other models from the same provider alongside models that score closest.
- Sonnet 566.6Cost $688 · Lift +43.8 · 846s
- Opus 570.0Cost $1,012 · Lift +32.8 · 342s
- Fable 5.172.7Cost $1,655 · Lift +30.3 · 512s
- Opus 5.575.4Cost $949 · Lift +31.2 · 512s
- GPT-6 Sol66.6Cost $183 · Lift +28.7 · 260s
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Claude Sonnet 5 | 66.6 | +43.8 | $688 | 846s |
| Opus 5Claude Opus 5 | 70.0 | +32.8 | $1,012 | 342s |
| Fable 5.1Claude Fable 5.1 | 72.7 | +30.3 | $1,655 | 512s |
| Opus 5.5Claude Opus 5.5 | 75.4 | +31.2 | $949 | 512s |
| GPT-6 SolGPT-6 Sol | 66.6 | +28.7 | $183 | 260s |
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.
# Claude Sonnet 5 · Search Capability Leaderboard
- Search Intelligence Score: 66.6 (#8 in Search Intelligence)
- Without search: 22.8 · Lift from search +43.8
- Cost per 1K tasks: $688 (#11 in Search Efficiency)
- Time per task: 846s
- Lab: Anthropic · Model id: claude-sonnet-5
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 82.8 | 32.5 |
| HLE | 45.0 | 25.0 |
| WISER | 72.0 | 11.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Claude Sonnet 5 | 66.6 | +43.8 | $688 | 846s |
| Claude Opus 5 | 70.0 | +32.8 | $1,012 | 342s |
| Claude Fable 5.1 | 72.7 | +30.3 | $1,655 | 512s |
| Claude Opus 5.5 | 75.4 | +31.2 | $949 | 512s |
| GPT-6 Sol | 66.6 | +28.7 | $183 | 260s |
Latest update September 25, 2026. Methodology: /leaderboard#methodology