BLINK
BLINK: Multimodal Large Language Models Can See but Not Perceive. A benchmark for multimodal language models focusing on core visual perception abilities. Reformats 14 classic computer vision tasks into 3,807 multiple-choice questions paired with single or multiple images and visual prompting. Tasks include relative depth estimation, visual correspondence, forensics detection, multi-view reasoning, counting, object localization, and spatial reasoning that humans can solve 'within a blink'.
Qwen3 VL 235B A22B Instruct from Alibaba Cloud / Qwen Team currently leads the BLINK leaderboard with a score of 0.707 across 11 evaluated AI models.
What BLINK measures
BLINK is a multimodal benchmark that evaluates large language models on vision, multimodal, reasoning, spatial reasoning, and 3d tasks. LLM Stats tracks 11 models on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.7, with the leader reaching 0.7.
Compare leaders on the best AI for vision, best AI for multimodal, best AI for reasoning, best AI for spatial reasoning and best AI for 3d leaderboards.
Publication
- Paper
- BLINK: Multimodal Large Language Models Can See but Not Perceive
- Authors
- Xingyu Fu, Yushi Hu, Bangzheng Li, Yu Feng, and 6 others
- Published
- arXiv
- 2404.12390
Abstract
We introduce Blink, a new benchmark for multimodal language models (LLMs) that focuses on core visual perception abilities not found in other evaluations. Most of the Blink tasks can be solved by humans "within a blink" (e.g., relative depth estimation, visual correspondence, forensics detection, and multi-view reasoning). However, we find these perception-demanding tasks cast significant challenges for current multimodal LLMs because they resist mediation through natural language. Blink reformats 14 classic computer vision tasks into 3,807 multiple-choice questions, paired with single or multiple images and visual prompting. While humans get 95.70% accuracy on average, Blink is surprisingly challenging for existing multimodal LLMs: even the best-performing GPT-4V and Gemini achieve accuracies of 51.26% and 45.72%, only 13.17% and 7.63% higher than random guessing, indicating that such perception abilities have not "emerged" yet in recent multimodal LLMs. Our analysis also highlights that specialist CV models could solve these problems much better, suggesting potential pathways for future improvements. We believe Blink will stimulate the community to help multimodal LLMs catch up with human-level visual perception.
Qwen3 VL 235B A22B Instruct leads with 70.7%, followed by Qwen3 VL 8B Instruct at 69.1% and Qwen3 VL 8B Thinking at 68.7%.
Progress Over Time
Interactive timeline showing model performance evolution on BLINK
BLINK Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | 236B | 262K | $0.30 / $1.49 | ||
| 2 | Alibaba Cloud / Qwen Team | 9B | 262K | $0.08 / $0.50 | ||
| 3 | Alibaba Cloud / Qwen Team | 9B | 262K | $0.18 / $2.09 | ||
| 4 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 5 | Alibaba Cloud / Qwen Team | 31B | — | — | ||
| 6 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 7 | Alibaba Cloud / Qwen Team | 236B | — | — | ||
| 8 | Alibaba Cloud / Qwen Team | 4B | 262K | $0.10 / $0.60 | ||
| 9 | Alibaba Cloud / Qwen Team | 31B | — | — | ||
| 10 | Alibaba Cloud / Qwen Team | 4B | 262K | $0.10 / $1.00 | ||
| 11 |  Microsoft | 6B | — | — |
FAQ
Common questions about BLINK.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions