Mathematical Reasoning on GeoQA (test)
75.07AccuracyVIRC-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| VIRC-7B#Params=7B, Model Category=Open-Source Reasoning Model2025.12 | 75.07 | |
| Qwen3-VL-8B-Instruct#Params=8B, Model Category=Open-Source General Model, tool=true2025.12 | 67.37 | |
| VIRC-3B#Params=3B, Model Category=Open-Source Reasoning Model2025.12 | 67.37 | |
| MINT-CoT-7B#Params=7B, Model Category=Open-Source Reasoning Model2025.12 | 64.72 | |
| MM-Eureka#Params=7B, Model Category=Open-Source Reasoning Model2025.12 | 62.86 | |
| Pixel Reasoner#Params=7B, Model Category=Open-Source Reasoning Model2025.12 | 53.05 | |
| InternVL2.5-8B-MPO#Params=8B, Model Category=Open-Source General Model2025.12 | 52.2 | |
| Claude 3.5 Sonnet#Params=-, Model Category=Closed-Source Model2025.12 | 50.8 | |
| DeepEyes#Params=7B, Model Category=Open-Source Reasoning Model2025.12 | 49.8 | |
| DAPO + AT-RLModel=Qwen2.5-VL-7B2026.02 | 48.55 | |
| Hint-GRPO-Qwen2-VL-7B#Params=7B, Model Category=Open-Source Reasoning Model2025.12 | 48.14 | |
| DAPOModel=Qwen2.5-VL-7B2026.02 | 46.95 | |
| R1-VL-7B#Params=7B, Model Category=Open-Source Reasoning Model2025.12 | 46.86 | |
| GSPOModel=Qwen2.5-VL-7B2026.02 | 46.8 | |
| Mini-o3#Params=7B, Model Category=Open-Source Reasoning Model2025.12 | 46.02 | |
| GRPOModel=Qwen2.5-VL-7B2026.02 | 45.92 | |
| Hint-GRPO-Qwen2.5-VL-3B#Params=3B, Model Category=Open-Source Reasoning Model2025.12 | 44.3 | |
| LLaVA-OV-Qwen2-7b-ov#Params=7B, Model Category=Open-Source General Model2025.12 | 44.16 | |
| Zero-shotModel=Qwen2.5-VL-7B2026.02 | 44.05 | |
| DAPO + AT-RLModel=Qwen2.5-VL-3B2026.02 | 43.85 | |
| Qwen2.5-VL-7B-Instruct#Params=7B, Model Category=Open-Source Reasoning Model2025.12 | 43.5 | |
| FT-RLModel=Qwen2.5-VL-7B2026.02 | 43.2 | |
| DAPOModel=Qwen2.5-VL-3B2026.02 | 41.7 | |
| GSPOModel=Qwen2.5-VL-3B2026.02 | 41.65 | |
| GRPOModel=Qwen2.5-VL-3B2026.02 | 40.65 | |
| GPT-4o#Params=-, Model Category=Closed-Source Model2025.12 | 40.53 | |
| Qwen2.5-VL-3B-Instruct#Params=3B, Model Category=Open-Source Reasoning Model2025.12 | 39.66 | |
| Zero-shotModel=Qwen2.5-VL-3B2026.02 | 38.72 | |
| FT-RLModel=Qwen2.5-VL-3B2026.02 | 36.2 | |
| InternVL2.5-8B#Params=8B, Model Category=Open-Source General Model2025.12 | 35.01 | |
| DeepSeek-VL2#Params=4.5B, Model Category=Open-Source General Model2025.12 | 25.33 |