Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific Graphics Program Synthesis on Scientific Graphics Program Synthesis Benchmark (test)
Loading...
7.12
Visual Fidelity (VF)
SciTikZer-8B
5.768
6.119
6.47
6.821
Apr 7, 2026
Visual Fidelity (VF)
Structural Correctness (SC)
Code Quality (CQ)
Average Score
Total Score
Updated 3mo ago
Evaluation Results
Method
Method
Links
Visual Fidelity (VF)
Structural Correctness (SC)
Code Quality (CQ)
Average Score
Total Score
SciTikZer-8B
Parameters=8B
2026.04
7.12
8.05
8.4
7.86
23.57
Gemini-2.5-Pro
Model tier=Pro
2026.04
7.03
8.01
8.29
7.78
23.33
GPT-5.1
2026.04
6.41
7.43
8.09
7.31
21.93
DeTikZify-v2.5-8B
Parameters=8B, Version...
2026.04
6.35
7.48
7.45
7.09
21.28
Qwen3-VL-Instruct-32B
Parameters=32B
2026.04
5.82
6.76
7.02
6.53
19.6
Feedback
Search any
task
Search any
task