Nejumi 4 - jaster (0-shot) - ALT Japanese-to-English: leaderboard
Japanese-to-English translation of Asian Language Treebank (ALT) parallel-corpus sentences, from the llm-jp-eval jaster suite as run 0-shot by Nejumi Leaderboard 4 (Weights & Biases Japan). Score is COMET (wmt22) x100 on Nejumi's sampled test split; higher is better.
Metric: COMET wmt22 (x100). Source: nejumi.ai. Saturation forecast: Estimated already saturated. 145 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol (Max) | 90.5 | #22 (GPT-5.6 Sol) |
| 2 | Gemini 3 Pro (Preview) | 90.45 | #71 |
| 3 | Gemini 3.1 Pro (Preview) | 90.35 | #64 |
| 4 | Gemini 3.6 Flash | 90.3 | #57 |
| 5 | Gemini 3.5 Flash | 90.25 | #66 |
| 6 | Claude Opus 5 (Max) | 90.24 | #16 (Claude Opus 5) |
| 7 | GPT-5.6 Terra (Max) | 90.24 | #40 (GPT-5.6 Terra) |
| 8 | Gemini 3 Flash (Preview) | 90.19 | #90 |
| 9 | GPT-5.4 (2026-03-05) (xHigh) | 90.15 | #63 (GPT-5.4 (2026-03-05)) |
| 10 | GPT-5.1 (2025-11-13) (High) | 90.15 | #107 (GPT-5.1 (2025-11-13)) |
| 11 | GPT-5 (2025-08-07) (High) | 90.14 | |
| 12 | Claude Opus 4.6 (Thinking) | 90.13 | #67 (Claude Opus 4.6) |
| 13 | Kimi K3 (Thinking) | 90.12 | #35 (Kimi K3) |
| 14 | GPT-5.4 (2026-03-05) (High) | 90.1 | #63 (GPT-5.4 (2026-03-05)) |
| 15 | Kimi K3 (Max) | 90.09 | #35 (Kimi K3) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=nejumi-4-jaster-0-shot-alt-japanese-to-english · How It Works · Data refreshed daily, snapshot 2026-11-05.