HELM SeaHELM - UIT-VSFC — leaderboard
Metric: Macro F1 score. Source: crfm.stanford.edu. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.1 70B Instruct | 73.08 |
| 2 | Llama 3.3 70B Instruct | 70.73 |
| 3 | Qwen 2 72B Instruct | 70.02 |
| 4 | GPT-4o Mini (2024-07-18) | 69.12 |
| 5 | Gemini 2.0 Flash | 68.87 |
| 6 | Llama 3.1 405B Instruct | 66.42 |
| 7 | DeepSeek V3 | 65.82 |
| 8 | GPT-4o (2024-11-20) | 65.67 |
| 9 | Gemini 2.0 Flash Lite | 65.61 |
| 10 | Llama 4 Scout Instruct | 65.49 |
| 11 | Llama 4 Maverick Instruct FP8 | 65.34 |
| 12 | Qwen 2.5 72B Instruct | 64.18 |
| 13 | Claude 3.7 Sonnet (20250219) | 61.71 |
| 14 | Llama 3.2 90B Vision Instruct | 33.59 |
| 15 | DeepSeek R1 Distill Llama 8B | 5.44 |
Interactive version: theaggregate.ai/benchmark?slug=helm-seahelm-uit-vsfc · How the rankings work · Data refreshed daily, snapshot 2026-07-22.