ProactiveBench - ImageNet-C: leaderboard
Metric: Trajectory accuracy (%) on the corrupted ImageNet-C images: multi-turn multiple choice in which the model may name a category, abstain, or pick a proactive suggestion that yields a new frame, and a trajectory counts only when it ends in the correct category; samples a first-turn guess solves for at least 25% of the evaluated models are filtered out; higher is better. Source: arxiv.org. Saturation forecast: Around December 2027. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 | 68.2 | #240 |
| 2 | O4 Mini | 49 | #172 |
| 3 | InternVL3-38B | 45.5 | #395 |
| 4 | Qwen 2.5 VL 7B Instruct | 40.5 | #643 |
| 5 | InternVL3-78B | 39.8 | #345 |
| 6 | InternVL3-8B | 37.7 | #606 |
| 7 | GPT-5.2 | 36.6 | #105 |
| 8 | Qwen 2.5 VL 32B Instruct | 30.9 | #443 |
| 9 | Phi-4 Multimodal Instruct | 29.8 | #896 |
| 10 | Qwen 2.5 VL 72B Instruct | 29.2 | #364 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=proactivebench-imagenet-c · How It Works · Data refreshed daily, snapshot 2026-10-11.