Search Intelligence Score
66.6
+28.7 lift from search
050100
- Lift from search
- +28.7
- 37.9 without search
- Cost per 1K tasks
- $183
- #7 in Search Efficiency
- Time per task
- 260s
- Search plus inference time to complete one task
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA81.9 vs 54.8
- HLE48.0 vs 40.0
- WISER70.0 vs 19.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $165
- 90%
- Search
- $7.01
- 4%
- Extract
- $11.0
- 6%
Compared with
Other models from the same provider alongside models that score closest.
- GPT-6 Sol66.6Cost $183 · Lift +28.7 · 260s
- GPT-5.6 Sol67.7Cost $269 · Lift +26.3 · 107s
- GPT-6 Astra70.8Cost $401 · Lift +27.9 · 83.7s
- GPT-6 Luna61.9Cost $33.1 · Lift +33.9 · 391s
- GPT-5.6 Luna60.7Cost $36.2 · Lift +33.9 · 98.0s
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| GPT-6 Sol | 66.6 | +28.7 | $183 | 260s |
| GPT-5.6 SolGPT-5.6 Sol | 67.7 | +26.3 | $269 | 107s |
| GPT-6 AstraGPT-6 Astra | 70.8 | +27.9 | $401 | 83.7s |
| GPT-6 LunaGPT-6 Luna | 61.9 | +33.9 | $33.1 | 391s |
| 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.
# GPT-6 Sol · Search Capability Leaderboard
- Search Intelligence Score: 66.6 (#7 in Search Intelligence)
- Without search: 37.9 · Lift from search +28.7
- Cost per 1K tasks: $183 (#7 in Search Efficiency)
- Time per task: 260s
- Lab: OpenAI · Model id: gpt-6-sol
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 81.9 | 54.8 |
| HLE | 48.0 | 40.0 |
| WISER | 70.0 | 19.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| GPT-6 Sol | 66.6 | +28.7 | $183 | 260s |
| GPT-5.6 Sol | 67.7 | +26.3 | $269 | 107s |
| GPT-6 Astra | 70.8 | +27.9 | $401 | 83.7s |
| GPT-6 Luna | 61.9 | +33.9 | $33.1 | 391s |
| GPT-5.6 Luna | 60.7 | +33.9 | $36.2 | 98.0s |
Latest update September 25, 2026. Methodology: /leaderboard#methodology