multimodal benchmark
BLINK Leaderboard
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'.
Updated Aug 17, 2026
Models15
Model coverage15
MetricScore
EvidenceB
BLINK Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelBY | Score81.4% | Percentile100.0% | Participants15 | EvidenceC | Evaluated |
| Rank02 | ModelBY | Score79.4% | Percentile92.9% | Participants15 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score70.7% | Percentile85.7% | Participants15 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score69.1% | Percentile78.6% | Participants15 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score68.7% | Percentile71.4% | Participants15 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score68.5% | Percentile64.3% | Participants15 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score67.7% | Percentile57.1% | Participants15 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score67.3% | Percentile50.0% | Participants15 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score67.1% | Percentile42.9% | Participants15 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score65.8% | Percentile35.7% | Participants15 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score65.4% | Percentile28.6% | Participants15 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score63.4% | Percentile21.4% | Participants15 | EvidenceC | Evaluated |
| Rank13 | ModelLA | Score61.5% | Percentile14.3% | Participants15 | EvidenceC | Evaluated |
| Rank14 | ModelMI | Score61.3% | Percentile7.1% | Participants15 | EvidenceC | Evaluated |
| Rank15 | ModelCO | Score52.7% | Percentile0.0% | Participants15 | EvidenceC | Evaluated |
BLINK Highlights
The leading models and scores on this benchmark.
BLINK Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for BLINK
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis blink AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01BYSeed 2.1 ProByteDance
- Score
- 81.4%
Strengths
- Ranks #1 of 15 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures BLINK, not total model capability
- 02BYSeed 2.1 TurboByteDance
- Score
- 79.4%
Strengths
- Ranks #2 of 15 compared models
- 93th percentile on this benchmark
- C evidence result
Considerations
- This result measures BLINK, not total model capability
- 03ACQwen3 VL 235B A22B InstructAlibaba Cloud / Qwen Team
- Score
- 70.7%
Strengths
- Ranks #3 of 15 compared models
- 86th percentile on this benchmark
- C evidence result
Considerations
- This result measures BLINK, not total model capability
- 04ACQwen3 VL 8B InstructAlibaba Cloud / Qwen Team
- Score
- 69.1%
Strengths
- Ranks #4 of 15 compared models
- 79th percentile on this benchmark
- C evidence result
Considerations
- This result measures BLINK, not total model capability
- 05ACQwen3 VL 8B ThinkingAlibaba Cloud / Qwen Team
- Score
- 68.7%
Strengths
- Ranks #5 of 15 compared models
- 71th percentile on this benchmark
- C evidence result
Considerations
- This result measures BLINK, not total model capability
Selection summary
Best AI Models for BLINK
Seed 2.1 Pro currently leads BLINK with 81.4%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is BLINK?
What BLINK measures and how its scores work.
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'.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- BLINK
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- blink|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about BLINK.
Which model scores highest on BLINK?
Seed 2.1 Pro is currently ranked first with 81.4%.
What does BLINK measure?
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'.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
15 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.