Nejumi 4 - jaster (0-shot) - KUCI: leaderboard
KUCI, Kyoto University commonsense inference with multiple-choice continuations, 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) | 93 | #64 |
| 2 | Gemini 3.6 Flash | 93 | #57 |
| 3 | Claude Opus 5 (Max) | 90 | #16 (Claude Opus 5) |
| 4 | GPT-5.1 (2025-11-13) (High) | 90 | #107 (GPT-5.1 (2025-11-13)) |
| 5 | Claude Opus 4 (Non-reasoning) | 90 | #170 (Claude Opus 4) |
| 6 | Gemini 3 Flash (Preview) | 89 | #90 |
| 7 | Kimi K3 (Max) | 89 | #35 (Kimi K3) |
| 8 | GPT-5.6 Terra (Max) | 89 | #40 (GPT-5.6 Terra) |
| 9 | DeepSeek V4 Pro (0813) (Max) | 89 | #58 (DeepSeek V4 Pro (0813)) |
| 10 | GPT-5 (2025-08-07) (High) | 89 | |
| 11 | Muse Spark Open (xHigh) | 89 | #42 (Muse Spark Open) |
| 12 | Claude Opus 4.1 (Thinking) | 89 | #146 (Claude Opus 4.1) |
| 13 | Gemini 3.5 Flash | 88 | #66 |
| 14 | GPT-5.6 Sol (Max) | 88 | #22 (GPT-5.6 Sol) |
| 15 | GPT-5.6 Luna (Max) | 88 | #79 (GPT-5.6 Luna) |
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-kuci · How It Works · Data refreshed daily, snapshot 2026-11-05.