LLM Stats (SimpleVQA): leaderboard
Simple Visual QA: straightforward factual questions about images testing basic visual perception and object recognition accuracy.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around January 2027. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5V Turbo | 78.2 | #166 |
| 2 | Seed 2.1 Pro | 74.5 | #67 |
| 3 | Muse Spark Open | 73.6 | #54 |
| 4 | Muse Spark | 71.3 | #64 |
| 5 | Kimi K2.5 | 71.2 | #144 |
| 6 | Seed 2.1 Turbo | 71.1 | #86 |
| 7 | Seed 2.0 Mini | 68.7 | #276 |
| 8 | Qwen 3.6 Plus | 67.3 | #120 |
| 9 | Seed 1.8 | 65.4 | #139 |
| 10 | Qwen 3.5 122B A10B | 61.7 | #173 |
| 11 | Qwen 3 VL 235B A22B (Thinking) | 61.3 | #238 (Qwen 3 VL 235B A22B) |
| 12 | Qwen 3.6 35B A3B | 58.9 | #226 |
| 13 | Qwen 3.5 35B A3B | 58.3 | #256 |
| 14 | Qwen 3.6 27B | 56.1 | #170 |
| 15 | Qwen 3.5 27B | 56 | #187 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-simplevqa · How It Works · Data refreshed daily, snapshot 2026-10-20.