Search Capability Leaderboard
Pareto 26.9
Unbiased AI
3Bronze · Search Intelligence
#8 in Search Efficiency
Search Intelligence Score
72.5
+32.8 lift from search
050100
- Lift from search
- +32.8
- 39.7 without search
- Cost per 1K tasks
- $184
- #8 in Search Efficiency
- Time per task
- 211s
- Search plus inference time to complete one task
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA87.6 vs 47.1
- HLE58.0 vs 52.0
- WISER72.0 vs 20.0
Cost per 1K tasks
This run reports model inference cost without a complete search and extract breakdown. The available total is $184 per 1,000 tasks.
Compared with
Other models from the same provider alongside models that score closest.
- Pareto 26.972.5Cost $184 · Lift +32.8 · 211s
- Fable 5.172.7Cost $1,655 · Lift +30.3 · 512s
- GPT-6 Astra70.8Cost $401 · Lift +27.9 · 83.7s
- GPT-6.1 Sol70.4Cost $130 · Lift +30.6 · 353s
- Opus 570.0Cost $1,012 · Lift +32.8 · 342s
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Pareto 26.9 | 72.5 | +32.8 | $184 | 211s |
| Fable 5.1Claude Fable 5.1 | 72.7 | +30.3 | $1,655 | 512s |
| GPT-6 AstraGPT-6 Astra | 70.8 | +27.9 | $401 | 83.7s |
| GPT-6.1 SolGPT-6.1 Sol | 70.4 | +30.6 | $130 | 353s |
| Opus 5Claude Opus 5 | 70.0 | +32.8 | $1,012 | 342s |
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 30, 2026. Full methodology.
# Pareto 26.9 · Search Capability Leaderboard
- Search Intelligence Score: 72.5 (#3 in Search Intelligence)
- Without search: 39.7 · Lift from search +32.8
- Cost per 1K tasks: $184 (#8 in Search Efficiency)
- Time per task: 211s
- Medals: Bronze, Search Intelligence
- Lab: Unbiased AI · Model id: unbiased/pareto-26.9
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 87.6 | 47.1 |
| HLE | 58.0 | 52.0 |
| WISER | 72.0 | 20.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Pareto 26.9 | 72.5 | +32.8 | $184 | 211s |
| Claude Fable 5.1 | 72.7 | +30.3 | $1,655 | 512s |
| GPT-6 Astra | 70.8 | +27.9 | $401 | 83.7s |
| GPT-6.1 Sol | 70.4 | +30.6 | $130 | 353s |
| Claude Opus 5 | 70.0 | +32.8 | $1,012 | 342s |
Latest update September 30, 2026. Methodology: /leaderboard#methodology