HELM SeaHELM - IndoNLI — leaderboard
Metric: EM. Source: crfm.stanford.edu. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2 72B Instruct | 86 |
| 2 | Claude 3.7 Sonnet (20250219) | 85.8 |
| 3 | Qwen 2.5 72B Instruct | 83.2 |
| 4 | GPT-4o (2024-11-20) | 83 |
| 5 | GPT-4o Mini (2024-07-18) | 81.3 |
| 6 | Gemini 2.0 Flash | 80 |
| 7 | Gemini 2.0 Flash Lite | 76.8 |
| 8 | Llama 3.1 405B Instruct | 70.9 |
| 9 | Llama 3.3 70B Instruct | 52.2 |
| 10 | Llama 3.1 70B Instruct | 37.1 |
| 11 | DeepSeek R1 Distill Llama 8B | 36.5 |
| 12 | Llama 4 Scout Instruct | 32.2 |
| 13 | Gemma 2 9B (IT) | 24.1 |
| 14 | Llama 3.2 90B Vision Instruct | 10.8 |
| 15 | Gemma 2 27B (IT) | 7.1 |
Interactive version: theaggregate.ai/benchmark?slug=helm-seahelm-indonli · How the rankings work · Data refreshed daily, snapshot 2026-07-22.