Search Capability Leaderboard
Qwen3.8 Max
QwenClosed
Evaluated
#20 in Search Intelligence · #13 in Search Efficiency
Search Intelligence Score
66.0
+37.1 lift from search
050100
- Lift from search
- +37.1
- 28.9 without search
- Cost per 1K tasks
- $221
- #13 in Search Efficiency
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA88.1 vs 38.7
- HLE40.0 vs 40.0
- WISER70.0 vs 8.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $205
- 93%
- Search
- $3.96
- 2%
- Extract
- $11.9
- 5%
Compared with
Other models from the same provider alongside models that score closest.
- Qwen3.8 Max66.0Cost $221 · Lift +37.1
- Grok 4.766.0Cost $252 · Lift +44.8
- Muse Spark 1.366.1Cost $142 · Lift +35.8
- Sonnet 566.6Cost $688 · Lift +43.8
- GPT-6 Sol66.6Cost $183 · Lift +28.7
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| Qwen3.8 Max | 66.0 | +37.1 | $221 |
| Grok 4.7Grok 4.7 Medium | 66.0 | +44.8 | $252 |
| Muse Spark 1.3Muse Spark 1.3 | 66.1 | +35.8 | $142 |
| Sonnet 5Claude Sonnet 5 | 66.6 | +43.8 | $688 |
| GPT-6 SolGPT-6 Sol | 66.6 | +28.7 | $183 |
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.
# Qwen3.8 Max · Search Capability Leaderboard
- Search Intelligence Score: 66.0 (#20 in Search Intelligence)
- Without search: 28.9 · Lift from search +37.1
- Cost per 1K tasks: $221 (#13 in Search Efficiency)
- Evaluated:
- Lab: Qwen · Weights: Closed · Model id: qwen/qwen3.8-max
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 88.1 | 38.7 |
| HLE | 40.0 | 40.0 |
| WISER | 70.0 | 8.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| Qwen3.8 Max | 66.0 | +37.1 | $221 |
| Grok 4.7 Medium | 66.0 | +44.8 | $252 |
| Muse Spark 1.3 | 66.1 | +35.8 | $142 |
| Claude Sonnet 5 | 66.6 | +43.8 | $688 |
| GPT-6 Sol | 66.6 | +28.7 | $183 |
Leaderboard last updated . Methodology: /leaderboard#methodology