Share your thoughts, 1 month free Claude Pro on usSee more

Scientific Graphics Program Synthesis on SciTikZ-Bench

97.2Success Rate

SciTikZer-8B

Updated 3mo ago

Evaluation Results

Method	Links
SciTikZer-8B 2026.04		97.2	93.8	96.5	92.3	94.9	29.7	27.7	72.5	74.6	10.9	8.4	42.8	28.9
SciTikZer-4B 2026.04		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
DeTikZify-V2.5-8B 2026.04		93.1	88.9	95.4	87.1	93.6	37.3	32.7	70.4	75.6	15.9	9.7	43	30.4
Qwen3-VL-235B-A22B 2026.04		92.1	86.8	94.2	84.8	92	43.8	39	66.6	72.2	19.2	12.3	45.2	23.3
Claude-4.5-Sonnet 2026.04		91	86.4	94.9	84.4	92.7	40.9	35.1	66.2	72.8	20.2	12.3	47	19.6
GPT-5.1 2026.04		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 2026.04		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
DeTikZify-V2-8B 2026.04		85.3	80.3	94.1	78.9	92.5	42.2	32.2	65.3	76.6	23.2	9.9	42.9	28.8
VinciCoder-8B 2026.04		83.6	78.2	93.4	76.3	91.2	50	40.2	60.4	72.3	26.3	11.9	47.8	23.8
Qwen3-VL-32B 2026.04		82.8	77.6	93.7	75.6	91.3	52.6	42.7	59.3	71.6	28.2	13.3	50.1	19.1
ImgTikZ 2026.04		81.8	76.8	93.9	75.4	92.2	49.9	38.8	58.9	72	27.3	11.2	48.3	20.2
DeTikZify-DS-7B 2026.04		77.4	70.8	91.4	69.5	89.8	56	43.2	55.3	71.4	36.6	18.1	49.3	18.9
GPT-5-Mini 2026.04		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
DeTikZify-CL-7B 2026.04		77.1	70.1	91	68.8	89.3	56.5	43.6	54.9	71.2	36.4	17.5	47.6	19.5
InternVL3.5-14B 2026.04		76.3	68	89.1	66.3	86.9	62.2	50.4	55.8	73.1	42.5	24.6	50	16.6
Qwen3-VL-8B 2026.04		71	64.5	90.8	63.3	89.1	60.7	44.6	50.9	71.7	42.3	18.8	50.8	17
InternVL3.5-8B 2026.04		68.6	59.9	87.4	58.3	85	66.9	51.8	49.8	72.7	48.8	25.3	53.6	13.4
Qwen3-VL-4B 2026.04		68.1	61.5	90.3	60.5	88.9	64.2	47.4	49.1	72	45.1	19.4	51	15.9
DeepSeek-VL2 2026.04		63	55.9	88.7	55.4	88	67.3	48	44.3	70.4	48.8	18.7	56.5	18
InternVL3.5-4B 2026.04		53.7	46.1	85.8	45	83.9	74.8	53	38.7	72.1	60.8	27	54.5	11.8