Nejumi 4 - jaster (2-shot) - AIO: leaderboard
AIO (AI King), Japanese open-domain quiz question answering, from the llm-jp-eval jaster suite as run 2-shot by Nejumi Leaderboard 4 (Weights & Biases Japan). Score is character-level F1 x100 on Nejumi's sampled test split; higher is better.
Metric: Character F1 (x100). Source: nejumi.ai. Saturation forecast: Estimated already saturated. 145 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4 (Non-reasoning) | 96.86 | #170 (Claude Opus 4) |
| 2 | Gemini 3 Pro (Preview) | 96.26 | #71 |
| 3 | GPT-5.1 (2025-11-13) (High) | 96.18 | #107 (GPT-5.1 (2025-11-13)) |
| 4 | Gemini 3 Flash (Preview) | 95.84 | #90 |
| 5 | Claude Opus 4.1 (Thinking) | 95.41 | #146 (Claude Opus 4.1) |
| 6 | Gemini 3.6 Flash | 95.36 | #57 |
| 7 | GPT-5.6 Sol (Max) | 95.36 | #22 (GPT-5.6 Sol) |
| 8 | Claude Opus 4.7 (xHigh) | 95.29 | #51 (Claude Opus 4.7) |
| 9 | GPT-5.4 (2026-03-05) (High) | 95.12 | #63 (GPT-5.4 (2026-03-05)) |
| 10 | Gemini 3.5 Flash | 94.91 | #66 |
| 11 | GPT-5.4 (2026-03-05) (xHigh) | 94.88 | #63 (GPT-5.4 (2026-03-05)) |
| 12 | Claude Opus 4.8 (xHigh) | 94.86 | #39 (Claude Opus 4.8) |
| 13 | GPT-5.4 Mini (2026-03-17) (High) | 94.81 | #180 (GPT-5.4 Mini (2026-03-17)) |
| 14 | O1 (2024-12-17) (High) | 94.79 | #157 (O1 (2024-12-17)) |
| 15 | GPT-5.2 (2025-12-11) (xHigh) | 94.62 |
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-2-shot-aio · How It Works · Data refreshed daily, snapshot 2026-11-05.