Mathematical Reasoning on RBench-V (Overall)
16.4AccuracyGPT-OSS-120B + GeoTikzBridge-Base
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-OSS-120B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 16.4 | |
| Skywork-OR1-32B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 15 | |
| GPT-4oTikz-supplementation=false2026.03 | 14.1 | |
| GLM-4.5-Air-106B-A12B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 13.8 | |
| GLM4.5-V-106B-A12B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 13.3 | |
| Qwen3-30B-A3B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 12.8 | |
| GLM4.5-V-106B-A12BTikz-supplementation=false2026.03 | 12.5 | |
| InternVL3.5-38B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 12 | |
| InternVL3.5-38BTikz-supplementation=false2026.03 | 11.8 | |
| Qwen3-VL-30B-A3B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 11.7 | |
| DS-R1-Distill-Qwen-32B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 11.2 | |
| Qwen3-VL-30B-A3BTikz-supplementation=false2026.03 | 11 | |
| Qwen2.5-VL-72BTikz-supplementation=false2026.03 | 10.6 | |
| GLM-Z1-32B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 10.5 | |
| InternVL3-78BTikz-supplementation=false2026.03 | 10.1 | |
| Qwen2.5-VL-32BTikz-supplementation=false2026.03 | 10 |