Search Capability Leaderboard
Ember-1
Fireworks AI
#10 in Search Intelligence · #14 in Search Efficiency
Search Intelligence Score
67.9
+38.0 lift from search
050100
- Lift from search
- +38.0
- 29.9 without search
- Cost per 1K tasks
- $335
- #14 in Search Efficiency
- Time per task
- 487s
- Search plus inference time to complete one task
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA86.7 vs 44.9
- HLE50.0 vs 33.0
- WISER67.0 vs 12.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $318
- 95%
- Search
- $5.47
- 2%
- Extract
- $11.9
- 4%
Compared with
Other models from the same provider alongside models that score closest.
- Ember-167.9Cost $335 · Lift +38.0 · 487s
- GPT-5.6 Sol67.7Cost $269 · Lift +26.3 · 107s
- Pareto 26.1068.6Cost $116 · Lift +33.8 · 436s
- Gemini 3.766.8Cost $130 · Lift +27.4 · 229s
- GPT-6 Sol66.6Cost $183 · Lift +28.7 · 260s
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Ember-1 | 67.9 | +38.0 | $335 | 487s |
| GPT-5.6 SolGPT-5.6 Sol | 67.7 | +26.3 | $269 | 107s |
| Pareto 26.10Pareto 26.10 | 68.6 | +33.8 | $116 | 436s |
| Gemini 3.7Gemini 3.7 Flash | 66.8 | +27.4 | $130 | 229s |
| GPT-6 SolGPT-6 Sol | 66.6 | +28.7 | $183 | 260s |
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 12, 2026. Full methodology.
# Ember-1 · Search Capability Leaderboard
- Search Intelligence Score: 67.9 (#10 in Search Intelligence)
- Without search: 29.9 · Lift from search +38.0
- Cost per 1K tasks: $335 (#14 in Search Efficiency)
- Time per task: 487s
- Lab: Fireworks AI · Model id: fireworks/ember-1
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 86.7 | 44.9 |
| HLE | 50.0 | 33.0 |
| WISER | 67.0 | 12.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| Ember-1 | 67.9 | +38.0 | $335 | 487s |
| GPT-5.6 Sol | 67.7 | +26.3 | $269 | 107s |
| Pareto 26.10 | 68.6 | +33.8 | $116 | 436s |
| Gemini 3.7 Flash | 66.8 | +27.4 | $130 | 229s |
| GPT-6 Sol | 66.6 | +28.7 | $183 | 260s |
Latest update October 12, 2026. Methodology: /leaderboard#methodology