PerSo - Belief: leaderboard
Table 5; 200 ChangeMyView threads; behavioral pair choice or 400 four-option cognitive instances per dimension; temperature 0, top-k 1; synthetic cognitive labels generated by Gemini 2.5 Pro; not persuasion win rate. Metric: Accuracy (%). Higher is better. Source: https://arxiv.org/html/2610.20548v1
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around January 2027. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 83 | #89 |
| 2 | Qwen 3.5 397B A17B (Non-reasoning) | 80.5 | #144 (Qwen 3.5 397B A17B) |
| 3 | DeepSeek V4 Pro | 80 | #99 |
| 4 | Gemini 2.5 Pro | 79.5 | #150 |
| 5 | Qwen 3.5 397B A17B (Thinking) | 79 | #144 (Qwen 3.5 397B A17B) |
| 6 | DeepSeek V3.1 | 76 | #261 |
| 7 | DeepSeek V3.2 | 73.75 | #201 |
| 8 | Qwen 3.5 35B A3B (Non-reasoning) | 71.75 | #250 (Qwen 3.5 35B A3B) |
| 9 | Qwen 3.5 35B A3B (Thinking) | 69.75 | #250 (Qwen 3.5 35B A3B) |
| 10 | Claude Haiku 4.5 | 68.5 | #275 |
| 11 | Qwen 3.5 4B (Non-reasoning) | 66 | #463 (Qwen 3.5 4B) |
| 12 | Qwen 3.5 4B (Thinking) | 63.5 | #463 (Qwen 3.5 4B) |
| 13 | Gemma 3 27B | 60 | #597 |
| 14 | Gemma 3 12B | 58.25 | #662 |
| 15 | Gemma 3 4B | 50 | #1074 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=perso-belief · How It Works · Data refreshed daily, snapshot 2026-10-16.