RealWorldQA: leaderboard
RealWorldQA: Evaluates multimodal understanding across image, text, chart, diagram, or cross-modal reasoning tasks.
Metric: RealWorldQA (verified). Source: x.ai. Source: benchmarklist.com. Source: llm-stats.com. Saturation forecast: Around October 2027. 51 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen3.8-Flash-Next | 88.5 | #72 |
| 2 | Qwen 3.8 Flash | 88.5 | #50 |
| 3 | Qwen 3.8 Max | 88 | #35 |
| 4 | Qwen3.8 Omni Flash | 87.7 | #28 |
| 5 | Qwen 3.7 Plus | 86.9 | #92 |
| 6 | Seed 2.1 Pro | 86.7 | #67 |
| 7 | Seed 2.1 Turbo | 86.3 | #86 |
| 8 | Qwen 3.8 27B | 85.9 | #105 |
| 9 | Qwen 3.6 Plus | 85.4 | #120 |
| 10 | Qwen 3.6 35B A3B | 85.3 | #226 |
| 11 | Qwen 3.5 122B A10B | 85.1 | #173 |
| 12 | Qwen 3.5 35B A3B | 84.1 | #256 |
| 13 | Qwen 3.6 27B | 84.1 | #170 |
| 14 | GPT-5.4 (xHigh) | 83.8 | #79 (GPT-5.4) |
| 15 | Qwen 3.5 27B | 83.7 | #187 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=realworldqa · How It Works · Data refreshed daily, snapshot 2026-10-20.