ProactBench - Critical: leaderboard
Pass rate on the Critical triggers of ProactBench (2026), turns 4 to 7 where the assistant must combine two or more disclosed details into a conclusion the user did not ask for; a GPT-5.4 judge grades each response Pass, Partial or Fail against a rubric written before the model answers. Percent; higher is better.
Metric: Pass rate (%) on the Critical triggers (turns 4-7: synthesising two or more disclosed anchors into a new conclusion) 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 | 75.4 | #54 | |
| 2 | Gemini 3.1 Pro (Preview) | 65.5 | #99 | |
| 3 | Kimi K2.6 | 64.4 | #192 | |
| 4 | Qwen 3.5 397B A17B Instruct | 63 | #285 | |
| 5 | Claude Opus 4.7 | 58.6 | #85 | |
| 6 | MiMo-V2.5-Pro | 53.2 | #284 | |
| 7 | Qwen 3.5 9B Instruct | 51.4 | #678 | |
| 8 | DeepSeek V4 Flash | 50.6 | #267 | |
| 9 | Gemini 2.5 Pro | Medium | 48.3 | #276 |
| 10 | O4 Mini (2025-04-16) | 44.8 | #370 | |
| 11 | Gemini 2.5 Flash | 37.9 | #463 | |
| 12 | GPT-4o (2024-11-20) | 18.5 | #859 | |
| 13 | Llama 4 Maverick | 14.2 | #1110 | |
| 14 | ProactBench Llama-3.2-8B (checkpoint unspecified) | 6.9 | ||
| 15 | Qwen 2.5 7B Instruct | 6.5 | #2723 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=proactbench-critical · How It Works · Data refreshed daily, snapshot 2026-11-21.