LifeEval (Open-Ended) - Goal-oriented Planning: leaderboard
Metric: GPT-5 judge score against the reference answer (0 to 1 in steps of 0.25, shown times 100) on the 367 open-ended Goal-oriented Planning questions of LifeEval, zero-shot, the model sees only the egocentric clip up to the question time (8 uniformly sampled frames for models without native video input), answer in fixed tags; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 26 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 69.89 | #91 |
| 2 | Gemini 2.5 Pro | 65.94 | #145 |
| 3 | GPT-5 Mini | 63.69 | #176 |
| 4 | Gemini 2.5 Flash | 59.54 | #237 |
| 5 | Grok 4 | 54.7 | #169 |
| 6 | GPT-4o | 52.72 | #333 |
| 7 | Qwen 3 VL 30B A3B (Thinking) | 44.28 | #338 (Qwen 3 VL 30B A3B) |
| 8 | Qwen 3 VL 30B A3B Instruct | 41.77 | #365 |
| 9 | Qwen 3 VL 8B (Thinking) | 41.69 | |
| 10 | Qwen 3 VL 8B Instruct | 37.6 | #401 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=lifeeval-open-ended-goal-oriented-planning · How It Works · Data refreshed daily, snapshot 2026-10-11.