Search Capability LeaderboardGoogle
Gemini 3.7 Flash
3Bronze · Search Efficiency
#10 in Search Intelligence
Search Intelligence Score
54.3
+25.3 lift from search
050100
- Lift from search
- +25.3
- 29.0 without search
- Cost per 1K tasks
- $61.1
- #3 in Search Efficiency
- Time per task
- 79.7s
- Search plus inference time to complete one task
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA43.0 vs 16.0
- HLE61.0 vs 54.0
- WISER59.0 vs 17.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $51.7
- 85%
- Search
- $6.16
- 10%
- Extract
- $3.25
- 5%
InferenceSearchExtract
Compared with
Other models from the same provider alongside models that score closest.
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Gemini 3.7 Flash | 54.3 | +25.3 | $61.1 | 79.7s |
| Gemini 3.8Gemini 3.8 Flash | 50.7 | +22.0 | $166 | 123s |
| Gemini 3Gemini 3 Flash | 45.3 | +21.0 | $199 | 116s |
| GPT-5.6 LunaGPT-5.6 Luna | 54.7 | +32.3 | $23.0 | 59.4s |
| Sonnet 5Claude Sonnet 5 | 53.7 | +33.3 | $223 | 83.3s |
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.
# Gemini 3.7 Flash · Search Capability Leaderboard
- Search Intelligence Score: 54.3 (#10 in Search Intelligence)
- Without search: 29.0 · Lift from search +25.3
- Cost per 1K tasks: $61.1 (#3 in Search Efficiency)
- Time per task: 79.7s
- Medals: Bronze, Search Efficiency
- Lab: Google · Model id: google/gemini-3.7-flash
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 43.0 | 16.0 |
| HLE | 61.0 | 54.0 |
| WISER | 59.0 | 17.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Gemini 3.7 Flash | 54.3 | +25.3 | $61.1 | 79.7s |
| Gemini 3.8 Flash | 50.7 | +22.0 | $166 | 123s |
| Gemini 3 Flash | 45.3 | +21.0 | $199 | 116s |
| GPT-5.6 Luna | 54.7 | +32.3 | $23.0 | 59.4s |
| Claude Sonnet 5 | 53.7 | +33.3 | $223 | 83.3s |
Latest update September 14, 2026. Methodology: /leaderboard#methodology