Search Intelligence Score
39.5
+27.2 lift from search
050100
- Lift from search
- +27.2
- 12.3 without search
- Cost per 1K tasks
- $21.4
- Below the median score of 61.9, so not ranked on cost
- Time per task
- 459s
- Search plus inference time to complete one task
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA49.5 vs 22.9
- HLE26.0 vs 11.0
- WISER43.0 vs 3.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $9.05
- 42%
- Search
- $4.37
- 20%
- Extract
- $7.96
- 37%
Compared with
Other models from the same provider alongside models that score closest.
- Laguna S 2.139.5Cost $21.4 · Lift +27.2 · 459s
- Nem 3.5 Ltng37.9Cost $12.1 · Lift +28.0 · 176s
- MiMo v2.549.5Cost $23.5 · Lift +36.1 · 894s
- MiniMax M352.6Cost $41.1 · Lift +29.5 · 291s
- Nem 3 Ultra53.0Cost $113 · Lift +37.7 · 328s
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Laguna S 2.1 | 39.5 | +27.2 | $21.4 | 459s |
| Nem 3.5 LtngNemotron 3.5 Lightning | 37.9 | +28.0 | $12.1 | 176s |
| MiMo v2.5MiMo v2.5 | 49.5 | +36.1 | $23.5 | 894s |
| MiniMax M3MiniMax M3 | 52.6 | +29.5 | $41.1 | 291s |
| Nem 3 UltraNemotron 3 Ultra 550B | 53.0 | +37.7 | $113 | 328s |
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.
# Laguna S 2.1 · Search Capability Leaderboard
- Search Intelligence Score: 39.5 (#26 in Search Intelligence)
- Without search: 12.3 · Lift from search +27.2
- Cost per 1K tasks: $21.4 (below the median score of 61.9, so not ranked on cost)
- Time per task: 459s
- Lab: Poolside · Model id: poolside/laguna-s-2.1
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 49.5 | 22.9 |
| HLE | 26.0 | 11.0 |
| WISER | 43.0 | 3.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Laguna S 2.1 | 39.5 | +27.2 | $21.4 | 459s |
| Nemotron 3.5 Lightning | 37.9 | +28.0 | $12.1 | 176s |
| MiMo v2.5 | 49.5 | +36.1 | $23.5 | 894s |
| MiniMax M3 | 52.6 | +29.5 | $41.1 | 291s |
| Nemotron 3 Ultra 550B | 53.0 | +37.7 | $113 | 328s |
Latest update September 25, 2026. Methodology: /leaderboard#methodology