ConsumerSimBench — leaderboard
Metric: Avg (95% CI) (self-reported). Source: benchmarklist.com. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 47.8 |
| 2 | Gemini 3 Flash (Preview) | 46.6 |
| 3 | Grok 4.20 | 44.9 |
| 4 | Qwen 3.5 397B A17B | 43.4 |
| 5 | DeepSeek V3 | 42.9 |
| 6 | Seed 1.8 | 42.4 |
| 7 | GPT-5.2 | 35.8 |
| 8 | MiniMax-M2.5 | 35.2 |
| 9 | Claude Opus 4.6 | 32.8 |
| 10 | MiMo-V2.5-Pro | 32.3 |
| 11 | Claude Sonnet 4.6 | 30.8 |
| 12 | GPT-4o | 29.7 |
Interactive version: theaggregate.ai/benchmark?slug=consumersimbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.