LiveChatBench: leaderboard
Metric: BLEU (0-100; Korean-to-English translation of 1,000 live-stream chat messages against human references; printed as a fraction). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 26.79 |
| 2 | Gemma 3 1B (IT) | 4.3 |
| 3 | Gemma 3 270M (IT) | 0.97 |
| 4 | Qwen 3 0.6B | 0.17 |
Interactive version: theaggregate.ai/benchmark?slug=livechatbench · How It Works · Data refreshed daily, snapshot 2026-09-26.