Search Intelligence Score
56.0
+27.2 lift from search
050100
- Lift from search
- +27.2
- 28.8 without search
- Cost per 1K tasks
- $161
- Below the median score of 63.5, so not ranked on cost
- Time per task
- —
- Time not reported for this run
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA68.9 vs 38.4
- HLE39.0 vs 38.0
- WISER60.0 vs 10.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $133
- 83%
- Search
- $8.38
- 5%
- Extract
- $19.3
- 12%
Compared with
Other models from the same provider alongside models that score closest.
- Beam56.0Cost $161 · Lift +27.2 · —
- GLM-5.254.3Cost $66.6 · Lift +35.9 · 301s
- Hunyuan 358.2Cost $28.4 · Lift +35.6 · 363s
- DS Pro58.4Cost $110 · Lift +27.9 · 383s
- DS Pro 081353.5Cost $234 · Lift +20.4 · 394s
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Beam | 56.0 | +27.2 | $161 | — |
| GLM-5.2GLM-5.2 | 54.3 | +35.9 | $66.6 | 301s |
| Hunyuan 3Hunyuan 3 | 58.2 | +35.6 | $28.4 | 363s |
| DS ProDeepSeek V4 Pro | 58.4 | +27.9 | $110 | 383s |
| DS Pro 0813DeepSeek V4 Pro (0813) | 53.5 | +20.4 | $234 | 394s |
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 17, 2026. Full methodology.
# Beam · Search Capability Leaderboard
- Search Intelligence Score: 56.0 (#37 in Search Intelligence)
- Without search: 28.8 · Lift from search +27.2
- Cost per 1K tasks: $161 (below the median score of 63.5, so not ranked on cost)
- Time per task: —
- Lab: Reflection AI · Weights: Open weights · Model id: reflection/beam
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 68.9 | 38.4 |
| HLE | 39.0 | 38.0 |
| WISER | 60.0 | 10.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Beam | 56.0 | +27.2 | $161 | — |
| GLM-5.2 | 54.3 | +35.9 | $66.6 | 301s |
| Hunyuan 3 | 58.2 | +35.6 | $28.4 | 363s |
| DeepSeek V4 Pro | 58.4 | +27.9 | $110 | 383s |
| DeepSeek V4 Pro (0813) | 53.5 | +20.4 | $234 | 394s |
Latest update October 17, 2026. Methodology: /leaderboard#methodology