Absurd World - Zero-Shot - CAR: 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 CAR ruleset, where hitting the net earns cars 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 | GPT-4o Mini | 100 | #1627 |
| 4 | DeepSeek R1 0528 | 100 | #425 |
| 5 | Llama 4 Maverick Instruct | 100 | #1125 |
| 6 | Hermes-3-Llama-3.1-405B | 100 | #1022 |
| 7 | Llama 3.1 Nemotron Ultra 253B v1 | 100 | #1027 |
| 8 | Qwen 2.5 72B Instruct | 99 | #1093 |
| 9 | Llama 3.1 405B Instruct | 97 | #1114 |
| 10 | Gemini 2.0 Flash (001) | 96 | #724 |
| 11 | Claude 3.5 Haiku | 92 | #1563 |
| 12 | Gemma 2 27B (IT) | 85 | #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-car · How It Works · Data refreshed daily, snapshot 2026-11-12.