ArgBench (Chain-of-Thought) - Quality Assessment: 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 quality assessment tasks under chain-of-thought prompting, times 100; higher is better.

Metric: Macro F1 (0-1, times 100) averaged over the argument quality assessment tasks, chain-of-thought prompting; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Llama 3.3 70B Instruct43.9#1385
2GPT-4.143.6#505
3Qwen 3 32B43#972
4Qwen 3 4B40.7#2348
5Mistral 7B Instruct (v0.3)40.4#6750
6DeepSeek R1 Distill Qwen 32B39.7#1834
7DeepSeek-R1-Distill-Qwen-7B38.9#8055
8Llama 3.1 8B Instruct36.7#4600
9Phi-mini-MoE-instruct35.8
10Mixtral 8x7B Instruct35.6#4696
11Mistral-Small-Instruct-240935.3#2016

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

Interactive version: theaggregate.ai/benchmark?slug=argbench-chain-of-thought-quality-assessment · How It Works · Data refreshed daily, snapshot 2026-11-21.