Search Capability Leaderboard
GPT-6 Astra
OpenAIClosed
Evaluated
#8 in Search Intelligence · #19 in Search Efficiency
Search Intelligence Score
70.8
+27.9 lift from search
050100
- Lift from search
- +27.9
- 43.0 without search
- Cost per 1K tasks
- $401
- #19 in Search Efficiency
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA89.5 vs 57.9
- HLE49.0 vs 52.0
- WISER74.0 vs 19.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $389
- 97%
- Search
- $3.54
- 1%
- Extract
- $8.24
- 2%
Compared with
Other models from the same provider alongside models that score closest.
- GPT-6 Astra70.8Cost $401 · Lift +27.9
- GPT-6.1 Sol70.4Cost $130 · Lift +30.6
- GPT-5.6 Sol67.7Cost $269 · Lift +26.3
- GPT-6 Sol66.6Cost $183 · Lift +28.7
- GPT-6 Luna61.9Cost $33.1 · Lift +33.9
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| GPT-6 Astra | 70.8 | +27.9 | $401 |
| GPT-6.1 SolGPT-6.1 Sol | 70.4 | +30.6 | $130 |
| GPT-5.6 SolGPT-5.6 Sol | 67.7 | +26.3 | $269 |
| GPT-6 SolGPT-6 Sol | 66.6 | +28.7 | $183 |
| GPT-6 LunaGPT-6 Luna | 61.9 | +33.9 | $33.1 |
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.
# GPT-6 Astra · Search Capability Leaderboard
- Search Intelligence Score: 70.8 (#8 in Search Intelligence)
- Without search: 43.0 · Lift from search +27.9
- Cost per 1K tasks: $401 (#19 in Search Efficiency)
- Evaluated:
- Lab: OpenAI · Weights: Closed · Model id: gpt-6-astra
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 89.5 | 57.9 |
| HLE | 49.0 | 52.0 |
| WISER | 74.0 | 19.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| GPT-6 Astra | 70.8 | +27.9 | $401 |
| GPT-6.1 Sol | 70.4 | +30.6 | $130 |
| GPT-5.6 Sol | 67.7 | +26.3 | $269 |
| GPT-6 Sol | 66.6 | +28.7 | $183 |
| GPT-6 Luna | 61.9 | +33.9 | $33.1 |
Leaderboard last updated . Methodology: /leaderboard#methodology