ProactBench - Weighted Score: leaderboard
Conversational proactivity on ProactBench (2026): at about 624 trigger points in 198 curated multi-turn dialogues the assistant should act on needs the user implied but never stated, and a GPT-5.4 judge grades each response Pass, Partial or Fail against a rubric written before the model answers. Weighted score counting Pass as 1 and Partial as 0.5, in percent; higher is better.
Metric: Weighted score (%): Pass counts 1, Partial 0.5 and Fail 0, averaged over all trigger points over the 198 curated dialogues of ProactBench (about 624 rubric-scored trigger points: 201 Emergent, 232 Critical, 191 Recovery), each trigger judged Pass, Partial or Fail by a GPT-5.4 judge against a rubric written before the model answers; dialogue histories are fixed from a curation run and the model regenerates only at the triggers, sampled once at temperature 0.7; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 16 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5.5 | 69.8 | #54 | |
| 2 | Claude Opus 4.7 | 60.6 | #85 | |
| 3 | Qwen 3.5 397B A17B Instruct | 60.6 | #285 | |
| 4 | Gemini 3.1 Pro (Preview) | 58.3 | #99 | |
| 5 | Qwen 3.5 9B Instruct | 57 | #678 | |
| 6 | Kimi K2.6 | 54.3 | #192 | |
| 7 | DeepSeek V4 Flash | 53.5 | #267 | |
| 8 | MiMo-V2.5-Pro | 52.8 | #284 | |
| 9 | Gemini 2.5 Pro | Medium | 50.3 | #276 |
| 10 | O4 Mini (2025-04-16) | 47.4 | #370 | |
| 11 | Gemini 2.5 Flash | 44.2 | #463 | |
| 12 | GPT-4o (2024-11-20) | 31.3 | #859 | |
| 13 | Llama 4 Maverick | 22.5 | #1110 | |
| 14 | Qwen 3 1.7B | 22 | #5860 | |
| 15 | Qwen 2.5 7B Instruct | 21.6 | #2723 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Example tasks
How long can a cooked mushroom and sage pot pie sit at room temp safely?
write a short note to my manager asking to use the entrance chalkboard this weekend
Interactive version: theaggregate.ai/benchmark?slug=proactbench-weighted-score · How It Works · Data refreshed daily, snapshot 2026-11-21.