MEGA-Bench Task - Figurative Speech Explanation — leaderboard

Metric: Task Score (%). Source: huggingface.co. 44 models tracked.

Top models

#ModelScore
1Gemma 3 27B (IT)86.9
2Gemini 2.5 Pro84.8
3Gemma 3 12B (IT)84.1
4GPT-4o Mini83.8
5Gemini 2.0 Flash (Preview)83.4
6GPT-4o83.1
7Claude 3.5 Sonnet (20240620)83.1
8Gemini 1.5 Pro (002)81.4
9Gemini 1.5 Flash (002)81.4
10Gemma 3 4B (IT)79
11InternVL3-14B78.6
12Claude 3.5 Sonnet (20241022)78.6
13InternVL3-78B78.3
14InternVL3-38B78.3
15Llama 4 Scout Base77.2

Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-figurative-speech-explanation · How the rankings work · Data refreshed daily, snapshot 2026-07-22.