ArgBench (Chain-of-Thought) - 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 chain-of-thought prompting, times 100; higher is better.

Metric: Macro F1 (0-1, times 100) averaged over the argument mining (unit segmentation and classification) 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
1GPT-4.154.2#506
2Llama 3.3 70B Instruct46#1394
3Qwen 3 32B45#983
4Mistral 7B Instruct (v0.3)44.1#6759
5Mixtral 8x7B Instruct40.9#4692
6DeepSeek R1 Distill Qwen 32B40.6#1844
7Mistral-Small-Instruct-240940#2026
8Phi-mini-MoE-instruct39.9
9Llama 3.1 8B Instruct39.6#4655
10Qwen 3 4B37.5#2379
11DeepSeek-R1-Distill-Qwen-7B37.3#7976

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=argbench-chain-of-thought-argument-mining · How It Works · Data refreshed daily, snapshot 2026-11-22.