Search Capability Leaderboard
Muse Spark 1.3
MetaClosed
Evaluated
#27 in Search Intelligence / #9 in Search Efficiency
Search Intelligence Score
66.1
+35.8 lift from search
050100
- Lift from search
- +35.8
- 30.3 without search
- Cost per 1K tasks
- $142
- #9 in Search Efficiency
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA85.2 vs 48.9
- HLE46.0 vs 30.0
- WISER67.0 vs 12.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $129
- 91%
- Search
- $4.55
- 3%
- Extract
- $8.38
- 6%
Compared with
Other models from the same provider alongside models that score closest.
- Muse Spark 1.366.1Cost $142 / Lift +35.8
- Muse Spark Open67.2Cost $171 / Lift +31.8
- Muse Wonder 1.071.3Cost $709 / Lift +36.0
- Qwen3.8 Max66.0Cost $221 / Lift +37.1
- Grok 4.766.0Cost $252 / Lift +44.8
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| Muse Spark 1.3 | 66.1 | +35.8 | $142 |
| Muse Spark OpenMuse Spark Open | 67.2 | +31.8 | $171 |
| Muse Wonder 1.0Muse Wonder 1.0 | 71.3 | +36.0 | $709 |
| Qwen3.8 MaxQwen3.8 Max | 66.0 | +37.1 | $221 |
| Grok 4.7Grok 4.7 Medium | 66.0 | +44.8 | $252 |
Search Intelligence Score averages accuracy on DSQA, HLE, and WISER with equal weight; cost is averaged the same way, with cost shown per 1,000 tasks. Evaluated . Leaderboard last updated . Full methodology.
# Muse Spark 1.3 / Search Capability Leaderboard
- Search Intelligence Score: 66.1 (#27 in Search Intelligence)
- Without search: 30.3 / Lift from search +35.8
- Cost per 1K tasks: $142 (#9 in Search Efficiency)
- Evaluated:
- Lab: Meta / Weights: Closed / Model id: meta/muse-spark-1.3
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 85.2 | 48.9 |
| HLE | 46.0 | 30.0 |
| WISER | 67.0 | 12.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| Muse Spark 1.3 | 66.1 | +35.8 | $142 |
| Muse Spark Open | 67.2 | +31.8 | $171 |
| Muse Wonder 1.0 | 71.3 | +36.0 | $709 |
| Qwen3.8 Max | 66.0 | +37.1 | $221 |
| Grok 4.7 Medium | 66.0 | +44.8 | $252 |
Leaderboard last updated . Methodology: /leaderboard#methodology