Search Intelligence Score
33.0
+27.0 lift from search
050100
- Lift from search
- +27.0
- 6.0 without search
- Cost per 1K tasks
- $28.3
- Below the median score of 51.2, so not ranked on cost
- Time per task
- 364s
- Search plus inference time to complete one task
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA29.0 vs 6.0
- HLE34.0 vs 9.0
- WISER36.0 vs 3.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $15.2
- 54%
- Search
- $7.17
- 25%
- Extract
- $5.92
- 21%
InferenceSearchExtract
Compared with
Other models from the same provider alongside models that score closest.
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Laguna S 2.1 | 33.0 | +27.0 | $28.3 | 364s |
| Nem 3.5 LtngNemotron 3.5 Lightning | 35.0 | +29.0 | $17.1 | 169s |
| Nem 3 UltraNemotron 3 Ultra 550B | 42.7 | +26.3 | $155 | 109s |
| DS Flash 0731DeepSeek V4 Flash (0731) | 43.7 | +21.0 | $9.45 | 88.0s |
| MiMo v2.5MiMo v2.5 | 45.0 | +32.3 | $26.2 | 203s |
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 14, 2026. Full methodology.
# Laguna S 2.1 · Search Capability Leaderboard
- Search Intelligence Score: 33.0 (#24 in Search Intelligence)
- Without search: 6.0 · Lift from search +27.0
- Cost per 1K tasks: $28.3 (below the median score of 51.2, so not ranked on cost)
- Time per task: 364s
- Lab: Poolside · Model id: poolside/laguna-s-2.1
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 29.0 | 6.0 |
| HLE | 34.0 | 9.0 |
| WISER | 36.0 | 3.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Laguna S 2.1 | 33.0 | +27.0 | $28.3 | 364s |
| Nemotron 3.5 Lightning | 35.0 | +29.0 | $17.1 | 169s |
| Nemotron 3 Ultra 550B | 42.7 | +26.3 | $155 | 109s |
| DeepSeek V4 Flash (0731) | 43.7 | +21.0 | $9.45 | 88.0s |
| MiMo v2.5 | 45.0 | +32.3 | $26.2 | 203s |
Latest update September 14, 2026. Methodology: /leaderboard#methodology