MEGA-Bench Task - Electricity Plot Future Prediction: leaderboard

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

Top models

#ModelScore
1Gemini 1.5 Flash (002)90.2
2Claude 3.5 Sonnet (20241022)88.1
3Gemini 2.5 Pro (Preview 03-25)87.4
4Gemini 1.5 Pro (002)84.9
5InternVL2.5-78B83.8
6Llama 4 Scout Base82.2
7Gemma 3 27B (IT)80.6
8Qwen 2 VL 72B79.7
9GPT-4o71.3
10InternVL3-8B71.3
11Claude 3.5 Sonnet (20240620)71
12Gemma 3 12B (IT)68.2
13Qwen 2 VL 7B64
14InternVL3-78B62.9
15Pixtral-12B48.8

Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-electricity-plot-future-prediction · How It Works · Data refreshed daily, snapshot 2026-09-05.