ConsumerSimBench - Negative Aspects: leaderboard
Metric: Criterion coverage (%) for T4 negative aspects (the event details consumers criticised): the share of a topic's criteria that the model's generated comment set covers, each criterion judged pointwise by GPT-5.2 against its definition and examples, averaged over the 1,553 RedNote trending topics of ConsumerSimBench (23,122 criteria in all); the model writes 10 to 30 realistic comments per topic from a neutral event description, one call at temperature 0.7; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 31.1 |
| 2 | Kimi K2.5 | 30.4 |
| 3 | Grok 4.20 | 27.2 |
| 4 | Gemini 3 Flash | 26.8 |
| 5 | GPT-5.2 | 25.6 |
| 6 | Qwen 3.5 397B A17B | 23.9 |
| 7 | MiMo-V2.5-Pro | 20.1 |
| 8 | Claude Opus 4.6 | 19.8 |
| 9 | MiniMax-M2.5 | 19.6 |
| 10 | Claude Sonnet 4.6 | 16.1 |
| 11 | GPT-4o | 12.1 |
Interactive version: theaggregate.ai/benchmark?slug=consumersimbench-negative-aspects · How It Works · Data refreshed daily, snapshot 2026-10-07.