Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Polyline Length Estimation on SpatialEval Beijing 1.0 (test)
Loading...
60.6
MAE
SRL
-29.936
581.182
1,192.3
1,803.418
Jun 3, 2026
MAE
Response Validity Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
MAE
Response Validity Rate
SRL
2026.06
60.6
-
SLM
base_model=Qwen3-8B, f...
2026.06
231
100
SpatialRGPT
2026.06
263.35
100
gemini-2.5-flash
2026.06
309.3
100
ChatGPT 5.1
2026.06
610.2
100
ChatGPT 5.1
mode=In-Context
2026.06
610.2
100
DeepSeek-R1-32B
2026.06
888
58.6
Qwen3-8B
mode=tuned
2026.06
1,034
100
Llama-3.3-70B
2026.06
1,093.7
100
Qwen3-8B
2026.06
2,324
97.7
Feedback
Search any
task
Search any
task