TuRTLe - Icarus Functionality — leaderboard
Metric: Average Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.5 | 79.59 |
| 2 | GLM-5 FP8 | 76.47 |
| 3 | DeepSeek R1 0528 | 75.53 |
| 4 | Gemma 4 31B (IT) | 75.25 |
| 5 | DeepSeek R1 | 74.77 |
| 6 | DeepSeek V3.1 Terminus | 72.87 |
| 7 | GPT-OSS-120B | 71.87 |
| 8 | GPT-OSS-20B | 62.33 |
| 9 | Llama 3.1 405B | 54.91 |
| 10 | QwQ-32B | 54.02 |
| 11 | Qwen 2.5 72B | 49.44 |
| 12 | Qwen 2.5 32B | 47.55 |
| 13 | starchat2-15B-v0.1 | 45.59 |
| 14 | Qwen 3 8B | 44 |
| 15 | Hermes-4-14B | 40.93 |
Interactive version: theaggregate.ai/benchmark?slug=turtle-icarus-functionality · How the rankings work · Data refreshed daily, snapshot 2026-07-22.