HELM SeaHELM - XNLI (vi) — leaderboard
Metric: EM. Source: crfm.stanford.edu. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-11-20) | 68.9 |
| 2 | Gemini 2.0 Flash | 65.9 |
| 3 | Claude 3.7 Sonnet (20250219) | 65.8 |
| 4 | GPT-4o Mini (2024-07-18) | 65.4 |
| 5 | Qwen 2.5 72B Instruct | 65.1 |
| 6 | Gemini 2.0 Flash Lite | 65 |
| 7 | Qwen 2 72B Instruct | 64.1 |
| 8 | Llama 3.1 405B Instruct | 60.8 |
| 9 | Llama 3.3 70B Instruct | 59.7 |
| 10 | Llama 4 Maverick Instruct FP8 | 30.7 |
| 11 | Gemma 2 9B (IT) | 25.1 |
| 12 | Gemma 2 27B (IT) | 23.1 |
| 13 | Llama 4 Scout Instruct | 21.2 |
| 14 | DeepSeek R1 Distill Llama 8B | 11.2 |
| 15 | Claude 3.5 Haiku (20241022) | 9.5 |
Interactive version: theaggregate.ai/benchmark?slug=helm-seahelm-xnli-vi · How the rankings work · Data refreshed daily, snapshot 2026-07-22.