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

Visual Reasoning on V*

92.7Accuracy

S1-VL-32B-RL

Updated 19d ago

Evaluation Results

Method	Links
S1-VL-32B-RL 2026.04		92.7
Penguin-VL 2026.03		90.2
Qwen3-VL 2026.03		90.1
S1-VL-32B-SFT 2026.04		90
Skywork-R1V4-30B 2026.04		88
Qwen3-VL-32B-Thinking 2026.04		86.91
Thyme-VL (7B) 2026.04		82.2
Qwen2.5-VL-32B 2026.04		81.2
InternVL3 78B 2026.01		81.15
Qwen3-VL-235B-A22B-Thinking 2026.04		80.6
Qwen 2.5 VL 72B 2026.01		80.1
Gemini 2.5 Pro 2026.04		79.1
Gemini-2.5-Pro 2026.05		79.1
ATLASGRPO 2026.05		77.9
Monet 2026.05		77.8
LVR 2026.05		77.5
ATLASSFT 2026.05		77.5
Qwen2.5-VL-7B 2026.04		76.4
MCOT 2026.05		76.4
LLaVA-OneVision-7B 2026.05		75.4
ATLASLA-GRPO 2026.05		75.4
VTS-V 2026.05		74.9
GPT 5 2026.01		74.87
GPT-5 2026.04		74.87
Intern-S1 (235B+6B) 2026.04		74.86
Gemini-2.0-Flash 2026.05		73.3
CoVT 2026.05		72.8
Gemini 2.5 Flash 2026.04		72.3
Qwen 2.5 VL 32B 2026.01		72.25
InternVL-3.5 2026.03		70.7
AdaReasoner 7B 2026.01		70.68
InternVL3-8B 2026.04		70.2
Qwen2.5-VL 2026.05		70.2
GPT 5 + Tools 2026.01		70.16
Gemini 2.5 flash 2026.01		68.59
DeepEyes 2026.01		67.54
Qwen 2.5 VL 72B + Tools 2026.01		65.97
OpenAI GPT-5 nano 2026.03		63.4
Qwen 2.5 VL 7B 2026.01		63.35
GPT-4o 2026.05		62.8
Gemma-3-27B 2026.05		62.3
Claude 4 sonnet 2026.01		59.69
Intern-S1-mini (8B) 2026.04		58.64
Bagel 2026.05		55.5
Qwen 2.5 VL 7B + Tools 2026.01		54.97
PixelReasoner 2026.01		53.4
Visual CoT 2026.05		44.5
Qwen 2.5 VL 3B 2026.01		43.98
V-Thinker 2026.05		41.4
MiniGPT-v2 2026.05		35.6
Anole 2026.05		25.4
Claude-4-Sonnet 2026.05		15.2