LLM Stats (InfoVQAtest): leaderboard
Test split of InfographicVQA with questions about complex infographics requiring layout understanding, numerical reasoning, and visual-textual integration.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Estimated already saturated. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K2.5 | 92.6 | #144 |
| 2 | Qwen 3 VL 235B A22B (Thinking) | 89.5 | #238 (Qwen 3 VL 235B A22B) |
| 3 | Qwen 3 VL 235B A22B Instruct | 89.2 | #273 |
| 4 | Qwen 3 VL 32B (Thinking) | 89.2 | #294 (Qwen 3 VL 32B) |
| 5 | Qwen 3 VL 32B Instruct | 87 | #283 |
| 6 | Qwen 3 VL 8B (Thinking) | 86 | |
| 7 | Qwen 3 VL 30B A3B (Thinking) | 86 | #351 (Qwen 3 VL 30B A3B) |
| 8 | Qwen 3 VL 8B Instruct | 83.1 | #420 |
| 9 | Qwen 3 VL 4B (Thinking) | 83 | #480 (Qwen 3 VL 4B) |
| 10 | Qwen 3 VL 30B A3B Instruct | 82 | #384 |
| 11 | Qwen 3 VL 4B Instruct | 80.3 | #515 |
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-infovqatest · How It Works · Data refreshed daily, snapshot 2026-10-20.