Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals into editable TikZ code. While TikZ is the de facto standard for scientific schematics due to its programmatic flexibility, its requirement for rigorous spatial precision presents a significant challenge for Multimodal Large Language Models. Progress is currently stifled by two primary gaps: (1) Data Quality Gap: existing image-TikZ corpora often lack strict executability and reliable visual alignment; (2) Evaluation Gap: a lack of benchmarks for both structural and visual fidelity. To address these, we present a closed-loop framework featuring: SciTikZ-230K, a large-scale, high-quality dataset from our Execution-Centric Data Engine covering 11 diverse scientific disciplines; SciTikZ-Bench, a multifaceted benchmark spanning from basic geometric constructs to intricate hierarchical schematics to evaluate both visual fidelity and structural logic. To further broaden the scope of visual-code optimization methodology, we introduce a novel Dual Self-Consistency Reinforcement Learning optimization paradigm, which utilizes Round-Trip Verification to penalize degenerate code and boost overall self-consistency. Empowered by these, our trained model SciTikZer-8B achieves state-of-the-art performance, consistently outperforming proprietary giants like Gemini-2.5-Pro and massive models like Qwen3-VL-235B-A22B-Instruct.
Figures & tables
Figure 1. Challenges in graphics program synthesis. Current open-source MLLMs struggle with the strict constraints of TikZ, exhibiting critical issues such as syntax hallucinations , dependency omissions and geometric misalignments .
Figure 2. Overview of the SciTikZ-230K Dataset. The chart above presents the hierarchical distribution of our full dataset, spanning 11 scientific domains and over 90 fine-grained sub-categories.
Figure 3. Overview of the Execution-Centric Data Engine . Beyond passive filtering, it uses MLLM-guided remediation to correct compilation faults and distill misaligned pairs, preserving diversity under strict visual-program alignment.
Figure 4. Overview of the SciTikZ Framework. The pipeline initializes with SFT and Curriculum Data Selection. Core DSC-RL integrates Visual Alignment for pixel precision and Self-Consistency Refinement via symbolic back-translation.
Model
Params
Compile
Visual Fidelity
Code Quality
Success Rate ↑
SigLIP ↑
CLIP ↑
LPIPS ↓
SSIM ↑
DreamSim ↓
TED Norm ↓
C-BLEU ↑
Proprietary Models
GPT-5-Mini
-
77.3
72.5 / 93.7
70.4 / 91.1
54.3 / 40.9
55.1 / 71.4
33.9 / 14.5
53.4
12.7
Claude-4.5-Sonnet
-
91.0
86.4 / 94.9
84.4 / 92.7
40.9 / 35.1
66.2 / 72.8
20.2 / 12.3
47.0
19.6
GPT-5.1
-
90.3
86.3 / 95.5
84.7 / 93.8
38.5 / 31.9
66.8 / 73.9
18.9 / 10.2
45.1
21.9
Gemini-2.5-Pro
-
88.9
85.5 / 96.2
83.6 / 94.1
40.2 / 32.7
65.8 / 74.1
19.8 / 9.8
46.7
23.6
Table 1. Main Results on SciTikZ-Bench. Zero-shot performance comparison. Visual metrics are reported as All / Success , while code metrics are calculated on all samples. The best results are highlighted in bold and the second best are underlined .
Scale
Training Stage
Compile Rate ↑
SigLIP ↑
CLIP ↑
LPIPS ↓
SSIM ↑
DreamSim ↓
TED Norm ↓
C-BLEU ↑
4B
Base (Qwen3-VL-4B)
68.1
61.5 / 90.3
60.5 / 88.9
64.2 / 47.4
49.1 / 72.0
45.1 / 19.4
51.0
15.9
+ SFT
80.4
74.3 / 92.5
72.4 / 90.1
52.5 / 40.9
58.8 / 73.2
32.8 / 16.4
45.6
30.7
+ SFT + Stage 1
90.7
86.0 / 94.8
84.0 / 92.6
37.5 / 31.1
66.7 / 73.6
19.4 / 11.1
44.1
29.1
+ SFT + Stage 1 + Stage 2
95.9
92.4 / 96.3
90.6 / 94.4
30.8 / 27.9
70.7 / 73.8
12.2 / 8.5
43.2
28.6
8B
Base (Qwen3-VL-8B)
71.0
64.5 / 90.8
63.3 / 89.1
60.7 / 44.6
50.9 / 71.7
42.3 / 18.8
50.8
17.0
+ SFT
81.0
75.1 / 92.7
73.3 / 90.5
51.4 / 40.0
59.8 / 73.8
30.3 / 14.0
45.2
31.6
Table 2. Progressive Training Framework Analysis on SciTikZ-Bench. This table disentangles the cumulative gains from each training stage: Base model, SFT, Stage 1 RL (Visual Alignment), and the full SciTikZer with Stage 2 DSC-RL.
Model
DSim ↑
KID ↓
cBLEU ↑
TED ↓
Compile ↑
Gemini-2.5-Pro
87.34
2.86
12.29
50.45
66.42
Qwen3-VL-8B
78.25
5.32
7.75
60.39
55.17
InternVL3.5-14B
72.51
7.70
10.53
53.45
65.31
Qwen3-VL-235B-A22B
83.91
2.66
16.05
49.80
87.82
DeTikZify-v2.5-8b
85.05
1.72
12.83
51.10
90.41
SciTikZer-8B (Ours)
88.29
1.14
16.17
48.83
94.46
Table 3. Performance on DaTikZ-v3 test set. The best results are highlighted in bold and the second best are underlined .
Figure 5. Impact of Data Curation. Curated data enhances both executability and visual fidelity in 4B and 8B models compared with raw data and DaTikZ-v3.
Figure 6. Ablation of Dual Self-Consistency (DSC). Comparison between standard RL and our full DSC method.
Figure 7. Case Analysis. A qualitative comparison of rendered TikZ code generated by different models. We compare SciTikZer-8B with SOTA baselines, including Gemini-2.5-Pro, DeTikZify-v2.5-8B, and Qwen3-VL-Instruct-32B.
Model
ChartMimic_direct_v2
Exec. Rate ↑
Low-L ↑
High-L ↑
VinciCoder-8B-SFT
87.9
75.2
79.3
VinciCoder-8B-RL
91.2
79.3
80.9
VinciCoder-8B-DSC
92.1
80.2
81.5
Table 4. Performance on ChartMimic_direct_v2. Comparison against standard VinciCoder RL method.
Table 5. Blind human evaluation carefully conducted on 300 randomly sampled benchmark test examples.