JP-TL-Bench - Japanese to English - Easy: leaderboard

Metric: LT Score (0-10; Easy items only; anchored pairwise Bradley-Terry, gemini-2.5-flash judge). Source: arxiv.org. Saturation forecast: Around November 2026. 64 models tracked.

Top models

#ModelScore
1Gemini 3 Flash (Preview)9.94
2Ministral-3-14B-Instruct-25129.9
3GPT-OSS-120B9.89
4Gemini 3 Pro (Preview)9.88
5DeepSeek V3.1 Terminus9.85
6Gemini 2.5 Flash9.83
7Qwen 3 235B A22B 2507 Instruct9.83
8Gemini 2.5 Pro9.79
9Kimi K2 09059.79
10Qwen 3 30B A3B 2507 Instruct9.7
11GPT-4o (2024-08-06)9.59
12Gemma 3 27B (IT)9.54
13NVIDIA-Nemotron-3-Nano-30B-A3B-BF169.47
14Llama 3.1 405B Instruct9.05
15Ling-flash-2.08.85

Interactive version: theaggregate.ai/benchmark?slug=jp-tl-bench-japanese-to-english-easy · How It Works · Data refreshed daily, snapshot 2026-09-25.