HELM SeaHELM - IndicXNLI — leaderboard
Metric: EM. Source: crfm.stanford.edu. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.1 405B Instruct | 63.3 |
| 2 | GPT-4o (2024-11-20) | 63.3 |
| 3 | Llama 3.1 70B Instruct | 62.9 |
| 4 | Claude 3.7 Sonnet (20250219) | 61.6 |
| 5 | Llama 3.3 70B Instruct | 56.4 |
| 6 | Llama 4 Scout Instruct | 55.4 |
| 7 | Gemini 2.0 Flash Lite | 55.3 |
| 8 | Qwen 2.5 72B Instruct | 49.3 |
| 9 | GPT-4o Mini (2024-07-18) | 47.8 |
| 10 | Gemini 2.0 Flash | 47.6 |
| 11 | Qwen 2 72B Instruct | 43.6 |
| 12 | Gemma 2 27B (IT) | 39.4 |
| 13 | Gemma 2 9B (IT) | 9.3 |
| 14 | Llama 4 Maverick Instruct FP8 | 7.4 |
| 15 | Llama 3.2 90B Vision Instruct | 4.4 |
Interactive version: theaggregate.ai/benchmark?slug=helm-seahelm-indicxnli · How the rankings work · Data refreshed daily, snapshot 2026-07-22.