ArgBench (Zero-Shot) - Argument Mining: leaderboard

ArgBench (2026) unifies 46 computational-argumentation tasks from 33 existing datasets into five skills. This board is the macro F1 averaged over the argument mining tasks under zero-shot prompting, times 100; higher is better.

Metric: Macro F1 (0-1, times 100) averaged over the argument mining (unit segmentation and classification) tasks, zero-shot prompting; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-4.153.6#505
2Llama 3.3 70B Instruct49#1385
3Mistral-Small-Instruct-240943.1#2016
4Mixtral 8x7B Instruct42.7#4696
5Qwen 3 32B41.5#972
6Llama 3.1 8B Instruct38.8#4600
7Mistral 7B Instruct (v0.3)38.5#6750
8Phi-mini-MoE-instruct38.5
9Qwen 3 4B37.8#2348
10DeepSeek R1 Distill Qwen 32B35.2#1834
11DeepSeek-R1-Distill-Qwen-7B30.6#8055

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=argbench-zero-shot-argument-mining · How It Works · Data refreshed daily, snapshot 2026-11-21.