Absurd World - Zero-Shot - MISSING: 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 MISSING ruleset, where a team scores when its shot misses the net, 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

#ModelScoreOverall rank
1Gemini 2.5 Flash100#452
2GPT-4.1 Mini100#775
3DeepSeek R1 0528100#425
4Llama 3.1 Nemotron Ultra 253B v1100#1027
5Llama 3.1 405B Instruct99#1114
6Llama 4 Maverick Instruct99#1125
7Hermes-3-Llama-3.1-405B99#1022
8Qwen 2.5 72B Instruct96#1093
9Gemini 2.0 Flash (001)92#724
10GPT-4o Mini91#1627
11Claude 3.5 Haiku89#1563
12Gemma 2 27B (IT)48#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-missing · How It Works · Data refreshed daily, snapshot 2026-11-12.