Nejumi 4 - jaster (0-shot) - JCommonsenseQA: leaderboard
JCommonsenseQA (JGLUE), five-choice Japanese commonsense question answering, 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: Estimated already saturated. 145 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 100 | #64 |
| 2 | Gemini 3 Flash (Preview) | 100 | #90 |
| 3 | Gemini 3.5 Flash | 100 | #66 |
| 4 | GPT-5.6 Sol (Max) | 100 | #22 (GPT-5.6 Sol) |
| 5 | GLM-5.3 (Max) | 100 | #44 (GLM-5.3) |
| 6 | Claude Opus 5 (Max) | 100 | #16 (Claude Opus 5) |
| 7 | Grok 4.5 (High) | 100 | #54 (Grok 4.5) |
| 8 | O1 (2024-12-17) (High) | 100 | #157 (O1 (2024-12-17)) |
| 9 | Hy4 preview (High) | 100 | #45 (Hy4 preview) |
| 10 | Gemini 2.5 Pro | 99 | #159 |
| 11 | Gemini 3 Pro (Preview) | 99 | #71 |
| 12 | Grok 4 | 99 | #189 |
| 13 | Claude Sonnet 4.5 (Thinking) | 99 | #148 (Claude Sonnet 4.5) |
| 14 | DeepSeek V4.1 Flash | 99 | #37 |
| 15 | Kimi K3 (Max) | 99 | #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-jcommonsenseqa · How It Works · Data refreshed daily, snapshot 2026-11-05.