Absurd World - Zero-Shot - ICE CREAM: leaderboard
Absurd World (Albright et al., 2026) zero-shot Determine Outcome task: from a text commentary of a five-shot-per-team penalty shootout under the ICE CREAM ruleset, where hitting the net earns ice cream instead of points, the model names the winner. Accuracy over 100 generated prompts per model, in percent; higher is better.
Metric: Determine-Outcome Accuracy (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 100 | #452 |
| 2 | GPT-4.1 Mini | 100 | #775 |
| 3 | Qwen 2.5 72B Instruct | 100 | #1093 |
| 4 | DeepSeek R1 0528 | 100 | #425 |
| 5 | Hermes-3-Llama-3.1-405B | 100 | #1022 |
| 6 | Llama 3.1 Nemotron Ultra 253B v1 | 100 | #1027 |
| 7 | GPT-4o Mini | 99 | #1627 |
| 8 | Llama 4 Maverick Instruct | 99 | #1125 |
| 9 | Llama 3.1 405B Instruct | 96 | #1114 |
| 10 | Gemini 2.0 Flash (001) | 96 | #724 |
| 11 | Claude 3.5 Haiku | 95 | #1563 |
| 12 | Gemma 2 27B (IT) | 87 | #1815 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=absurd-world-zero-shot-ice-cream · How It Works · Data refreshed daily, snapshot 2026-11-12.