ConsumerSimBench - Positive Aspects: leaderboard

ConsumerSimBench Positive Aspects measures whether the comments a model writes about 1,553 real RedNote trending topics reproduce the positive aspects that real consumers expressed (ConsumerSimBench, 2026). The score is the percent of the criteria in that family that the comments cover, judged by GPT-5.2; higher is better.

Metric: Criterion coverage (%) for T3 positive aspects (the event details consumers praised): 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 July 2027. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3 Flash63.8#175
2Gemini 3.1 Pro (Preview)61.2#99
3Grok 4.2060#301
4Qwen 3.5 397B A17B59.8#264
5Doubao Seed 1.8Thinking58.3#352
6Kimi K2.555.6#266
7ConsumerSimBench DeepSeek-V3 (checkpoint unspecified)54.8
8MiniMax-M2.548.3#600
9GPT-5.247.8#185
10Claude Sonnet 4.646#173
11MiMo-V2.5-Pro45.3#284
12Claude Opus 4.644.7#113
13GPT-4o43.5#751

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=consumersimbench-positive-aspects · How It Works · Data refreshed daily, snapshot 2026-11-21.