Search Capability Leaderboard
Pareto 26.10
Unbiased AI
3Bronze · Search Efficiency
#7 in Search Intelligence
Search Intelligence Score
68.6
+33.8 lift from search
050100
- Lift from search
- +33.8
- 34.8 without search
- Cost per 1K tasks
- $116
- #3 in Search Efficiency
- Time per task
- 436s
- Search plus inference time to complete one task
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA84.8 vs 52.5
- HLE43.0 vs 37.0
- WISER78.0 vs 15.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $106
- 91%
- Search
- $3.31
- 3%
- Extract
- $6.98
- 6%
Compared with
Other models from the same provider alongside models that score closest.
- Pareto 26.1068.6Cost $116 · Lift +33.8 · 436s
- Pareto 26.972.5Cost $184 · Lift +32.8 · 211s
- GPT-5.6 Sol67.7Cost $269 · Lift +26.3 · 107s
- Opus 570.0Cost $1,012 · Lift +32.8 · 342s
- Gemini 3.766.8Cost $130 · Lift +27.4 · 229s
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Pareto 26.10 | 68.6 | +33.8 | $116 | 436s |
| Pareto 26.9Pareto 26.9 | 72.5 | +32.8 | $184 | 211s |
| GPT-5.6 SolGPT-5.6 Sol | 67.7 | +26.3 | $269 | 107s |
| Opus 5Claude Opus 5 | 70.0 | +32.8 | $1,012 | 342s |
| Gemini 3.7Gemini 3.7 Flash | 66.8 | +27.4 | $130 | 229s |
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 October 5, 2026. Full methodology.
# Pareto 26.10 · Search Capability Leaderboard
- Search Intelligence Score: 68.6 (#7 in Search Intelligence)
- Without search: 34.8 · Lift from search +33.8
- Cost per 1K tasks: $116 (#3 in Search Efficiency)
- Time per task: 436s
- Medals: Bronze, Search Efficiency
- Lab: Unbiased AI · Model id: unbiased/pareto-26.10
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 84.8 | 52.5 |
| HLE | 43.0 | 37.0 |
| WISER | 78.0 | 15.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Pareto 26.10 | 68.6 | +33.8 | $116 | 436s |
| Pareto 26.9 | 72.5 | +32.8 | $184 | 211s |
| GPT-5.6 Sol | 67.7 | +26.3 | $269 | 107s |
| Claude Opus 5 | 70.0 | +32.8 | $1,012 | 342s |
| Gemini 3.7 Flash | 66.8 | +27.4 | $130 | 229s |
Latest update October 5, 2026. Methodology: /leaderboard#methodology