Nejumi 4 - jaster (0-shot) - JCoLA (in-domain): leaderboard
JCoLA in-domain split, Japanese grammatical acceptability judgments, from the llm-jp-eval jaster suite as run 0-shot by Nejumi Leaderboard 4 (Weights & Biases Japan). Score is exact match (%) on Nejumi's sampled test split; higher is better.
Metric: Exact match (%). Source: nejumi.ai. Saturation forecast: Not forecast. 145 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 86 | #90 |
| 2 | GPT-5.1 (2025-11-13) (High) | 84 | #107 (GPT-5.1 (2025-11-13)) |
| 3 | Gemini 3 Pro (Preview) | 83 | #71 |
| 4 | GPT-4.1 | 82 | #258 |
| 5 | Llama 3.1 405B Instruct FP8 | 82 | #400 |
| 6 | O1 (2024-12-17) (High) | 82 | #157 (O1 (2024-12-17)) |
| 7 | Claude Opus 4.6 (Thinking) | 81 | #67 (Claude Opus 4.6) |
| 8 | Gemini 3.5 Flash | 80 | #66 |
| 9 | GPT-4o (2024-11-20) | 80 | #392 |
| 10 | DeepSeek V3.2 (Thinking) | 80 | #210 (DeepSeek V3.2) |
| 11 | GPT-5.6 Luna (Max) | 80 | #79 (GPT-5.6 Luna) |
| 12 | DeepSeek V4 Pro (0813) (Max) | 80 | #58 (DeepSeek V4 Pro (0813)) |
| 13 | GPT-5.1 (2025-11-13) (Non-reasoning) | 80 | #107 (GPT-5.1 (2025-11-13)) |
| 14 | DeepSeek V4.1 Flash | 79 | #37 |
| 15 | Gemini 3.6 Flash | 79 | #57 |
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-jcola-in-domain · How It Works · Data refreshed daily, snapshot 2026-11-05.