IDP Leaderboard — leaderboard

IDP Leaderboard evaluates model capability on multimodal tasks from the linked upstream source with Overall Score as the primary reported metric.

Metric: Avg Score (%). Source: idp-leaderboard.org. Status: saturation imminent. 26 models tracked.

Top models

#ModelScore
1GPT-5.481
2GPT-5.279.1
3Gemini 3 Pro77.7
4Qwen 3.5 9B77.2
5Qwen 3 VL 235B A22B76.8
6Qwen 3.5 4B75.4
7Gemini 3 Flash75.3
8Claude Opus 4.674.1
9Claude Sonnet 4.673.9
10Qwen 3.5 2B71.9
11GPT-5 Mini69.9
12Gemini 3.1 Pro (Preview)69.8
13Mistral Small 469.6
14Qwen 3.5 0.8B64.8
15Claude Haiku 4.561.2

Interactive version: theaggregate.ai/benchmark?slug=idp-leaderboard · How the rankings work · Data refreshed daily, snapshot 2026-07-22.