Search Intelligence Score
62.7
+40.8 lift from search
050100
- Lift from search
- +40.8
- 21.9 without search
- Cost per 1K tasks
- $78.5
- #3 in Search Efficiency
- Time per task
- 308s
- Search plus inference time to complete one task
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA85.0 vs 34.6
- HLE41.0 vs 24.0
- WISER62.0 vs 7.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $68.3
- 87%
- Search
- $3.16
- 4%
- Extract
- $7.04
- 9%
Compared with
Other models from the same provider alongside models that score closest.
- GLM 5.362.7Cost $78.5 · Lift +40.8 · 308s
- GLM-5.254.3Cost $66.6 · Lift +35.9 · 301s
- DS Flash 4.162.7Cost $35.8 · Lift +35.7 · 549s
- GPT-6 Luna61.9Cost $33.1 · Lift +33.9 · 391s
- Kimi K364.2Cost $266 · Lift +33.6 · 432s
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| GLM 5.3 | 62.7 | +40.8 | $78.5 | 308s |
| GLM-5.2GLM-5.2 | 54.3 | +35.9 | $66.6 | 301s |
| DS Flash 4.1DeepSeek V4.1 Flash | 62.7 | +35.7 | $35.8 | 549s |
| GPT-6 LunaGPT-6 Luna | 61.9 | +33.9 | $33.1 | 391s |
| Kimi K3Kimi K3 | 64.2 | +33.6 | $266 | 432s |
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 September 25, 2026. Full methodology.
# GLM 5.3 · Search Capability Leaderboard
- Search Intelligence Score: 62.7 (#13 in Search Intelligence)
- Without search: 21.9 · Lift from search +40.8
- Cost per 1K tasks: $78.5 (#3 in Search Efficiency)
- Time per task: 308s
- Medals: Bronze, Search Efficiency
- Lab: Z.ai · Model id: z-ai/glm-5.3-openrouter
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 85.0 | 34.6 |
| HLE | 41.0 | 24.0 |
| WISER | 62.0 | 7.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks | Time per task |
|---|---|---|---|---|
| GLM 5.3 | 62.7 | +40.8 | $78.5 | 308s |
| GLM-5.2 | 54.3 | +35.9 | $66.6 | 301s |
| DeepSeek V4.1 Flash | 62.7 | +35.7 | $35.8 | 549s |
| GPT-6 Luna | 61.9 | +33.9 | $33.1 | 391s |
| Kimi K3 | 64.2 | +33.6 | $266 | 432s |
Latest update September 25, 2026. Methodology: /leaderboard#methodology