Evals for Every Language - Language sg: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 61.63 |
| 2 | Claude Opus 4.7 | 60.13 |
| 3 | GPT-5.5 | 57.94 |
| 4 | Qwen 3.6 Plus | 55.83 |
| 5 | Gemini 3.1 Flash Lite | 54.85 |
| 6 | Claude Opus 4.8 | 54.45 |
| 7 | Gemini 2.5 Pro | 52.7 |
| 8 | Grok 4.20 | 50.91 |
| 9 | Claude Sonnet 4.6 | 46.58 |
| 10 | GPT-5.4 | 45.95 |
| 11 | DeepSeek V3.1 | 42.21 |
| 12 | Qwen 3.6 Flash | 38.83 |
| 13 | GPT-5.2 | 38.39 |
| 14 | jamba-large-1.7 | 37.66 |
| 15 | GPT-5 | 36.94 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-sg · How It Works · Data refreshed daily, snapshot 2026-09-05.