Nejumi 4 - GLP - General Knowledge: leaderboard
Averages four closed-book jaster question sets, JCommonsenseQA, the multi-hop JEMHopQA, NIILC and the AIO quiz set, each taken as the mean of its 0-shot and 2-shot runs, together with the MT-Bench STEM questions rated by an LLM judge. Reported on a 0 to 100 scale where higher is better. Source: github.com/wandb/llm-leaderboard.
Metric: Score (%). Source: nejumi.ai. Saturation forecast: Around January 2027. 139 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 85.56 | #58 |
| 2 | Gemini 3.5 Flash | 85.27 | #60 |
| 3 | Gemini 3 Pro (Preview) | 85.16 | #66 |
| 4 | GPT-5.4 (2026-03-05) | 84.63 | #59 |
| 5 | GPT-5.5 (2026-04-23) | 84.45 | #22 |
| 6 | Gemini 3.6 Flash | 84.39 | #51 |
| 7 | Muse Spark Open | 84.17 | #54 |
| 8 | Gemini 3 Flash (Preview) | 84.15 | #82 |
| 9 | GPT-5.6 Sol | 83.89 | #19 |
| 10 | GPT-5.6 Terra | 83.78 | #41 |
| 11 | Claude Opus 4.1 | 83.02 | #140 |
| 12 | Claude Opus 4.5 | 82.97 | #83 |
| 13 | Claude Opus 4.7 | 82.89 | #49 |
| 14 | GPT-5 | 82.87 | #98 |
| 15 | GPT-5.2 | 82.65 | #110 |
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-glp-general-knowledge · How It Works · Data refreshed daily, snapshot 2026-10-20.