Search Capability Leaderboard
DeepSeek V4.1 Flash
DeepSeekOpen weights
Evaluated
#30 in Search Intelligence
Search Intelligence Score
62.7
+35.7 lift from search
050100
- Lift from search
- +35.7
- 27.0 without search
- Cost per 1K tasks
- $35.8
- Below the median score of 64.4, so not ranked on cost
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA82.1 vs 45.0
- HLE42.0 vs 26.0
- WISER64.0 vs 10.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $15.7
- 44%
- Search
- $6.52
- 18%
- Extract
- $13.6
- 38%
Compared with
Other models from the same provider alongside models that score closest.
- DS Flash 4.162.7Cost $35.8 · Lift +35.7
- DS Pro58.4Cost $110 · Lift +27.9
- DS Flash 4.1 101768.9Cost $125 · Lift +36.0
- GLM 5.362.7Cost $78.5 · Lift +40.8
- Haiku 5.562.9Cost $24.3 · Lift +39.4
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| DeepSeek V4.1 Flash | 62.7 | +35.7 | $35.8 |
| DS ProDeepSeek V4 Pro | 58.4 | +27.9 | $110 |
| DS Flash 4.1 1017DeepSeek V4.1 Flash (1017) | 68.9 | +36.0 | $125 |
| GLM 5.3GLM 5.3 | 62.7 | +40.8 | $78.5 |
| Haiku 5.5Claude Haiku 5.5 | 62.9 | +39.4 | $24.3 |
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.
# DeepSeek V4.1 Flash · Search Capability Leaderboard
- Search Intelligence Score: 62.7 (#30 in Search Intelligence)
- Without search: 27.0 · Lift from search +35.7
- Cost per 1K tasks: $35.8 (below the median score of 64.4, so not ranked on cost)
- Evaluated:
- Lab: DeepSeek · Weights: Open weights · Model id: deepseek/deepseek-v4.1-flash
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 82.1 | 45.0 |
| HLE | 42.0 | 26.0 |
| WISER | 64.0 | 10.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| DeepSeek V4.1 Flash | 62.7 | +35.7 | $35.8 |
| DeepSeek V4 Pro | 58.4 | +27.9 | $110 |
| DeepSeek V4.1 Flash (1017) | 68.9 | +36.0 | $125 |
| GLM 5.3 | 62.7 | +40.8 | $78.5 |
| Claude Haiku 5.5 | 62.9 | +39.4 | $24.3 |
Leaderboard last updated . Methodology: /leaderboard#methodology