MEGA-Bench - Skill: Planning And Decision Making: leaderboard
The "Skill: Planning And Decision Making" subtask of MEGA-Bench. TIGER-Lab multimodal evaluation with 500+ tasks across vision-language understanding, generation, and reasoning with 44 models.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around April 2027. 44 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 42.1 | #123 |
| 2 | Claude 3.5 Sonnet (20241022) | 29.1 | #291 |
| 3 | Gemini 2.0 Flash (Preview) | 25.8 | #370 |
| 4 | Gemini 1.5 Pro (002) | 23.9 | #349 |
| 5 | Claude 3.5 Sonnet (20240620) | 23.8 | #299 |
| 6 | GPT-4o | 22.9 | #343 |
| 7 | InternVL2.5-78B | 22.9 | #431 |
| 8 | Qwen 2 VL 72B | 21.6 | #460 |
| 9 | GPT-4o Mini | 19.4 | #599 |
| 10 | InternVL3-78B | 16.9 | #352 |
| 11 | Gemma 3 27B (IT) | 16.8 | #523 |
| 12 | GLM-4.1V-9B (Thinking) | 16.4 | #472 (GLM-4.1V-9B) |
| 13 | Gemini 1.5 Flash (002) | 16.2 | #583 |
| 14 | InternVL3-38B | 13.5 | #405 |
| 15 | Qwen 2 VL 7B | 12.7 | #750 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-skill-planning-and-decision-making · How It Works · Data refreshed daily, snapshot 2026-10-20.