Bongard in Wonderland: leaderboard
Visual abstract reasoning benchmark using classic Bongard problems. Models must identify discriminative visual concepts from sets of positive and negative examples. Hardcoded from arXiv:2410.19546.
Metric: Problems Solved (out of 100). Source: ml-research.github.io. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 64 | #98 |
| 2 | O3 | 53 | #124 |
| 3 | O1 | 43 | #183 |
| 4 | Claude 3.5 Sonnet | 31 | #350 |
| 5 | GPT-4o | 25 | #343 |
| 6 | Gemini 2.0 Flash | 25 | #342 |
| 7 | Gemini 1.5 Pro | 8 | #445 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=bongard-in-wonderland · How It Works · Data refreshed daily, snapshot 2026-10-20.