SAFARI - Task 1 (Few-Shot): leaderboard
Metric: Judge score (%, mean of HLM/PCC/RCC, judge Qwen3.6-Max). Source: arxiv.org. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5.1 | 72.6 |
| 2 | Gemini 3.5 Flash | 71.5 |
| 3 | DeepSeek V4 Flash | 71.4 |
| 4 | Qwen 3.5 397B A17B | 69.1 |
| 5 | MiniMax-M2.7 | 69 |
| 6 | DeepSeek V4 Pro | 68.5 |
| 7 | Qwen 3.5 122B A10B | 65.6 |
| 8 | GPT-5.5 | 65.3 |
| 9 | GPT-5.4 Mini | 59.8 |
Interactive version: theaggregate.ai/benchmark?slug=safari-task-1-few-shot · How It Works · Data refreshed daily, snapshot 2026-09-20.