Nejumi 4 - GLP - Function Calling: leaderboard
Nejumi 4 (Japanese, Weights & Biases), general language performance: the tool and function calling category.
Metric: Score (%). Source: nejumi.ai. Saturation forecast: Around 2029. 139 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 72.53 | #19 |
| 2 | Claude Opus 4.7 | 72.16 | #49 |
| 3 | Claude Opus 4.8 | 71.91 | #37 |
| 4 | Claude Opus 4.1 | 71.42 | #140 |
| 5 | Claude Opus 4.5 | 71.3 | #83 |
| 6 | Claude Opus 4 | 70.06 | #163 |
| 7 | Claude Opus 5 | 69.94 | #12 |
| 8 | Claude Opus 4.6 | 69.75 | #63 |
| 9 | Claude Fable 5 | 69.69 | #16 |
| 10 | Qwen 3.6 27B | 69.51 | #170 |
| 11 | Qwen 3.6 Max Preview | 69.44 | #85 |
| 12 | Claude Sonnet 4 | 68.95 | #199 |
| 13 | Gemini 3 Pro (Preview) | 68.77 | #66 |
| 14 | Gemini 3.1 Pro (Preview) | 68.64 | #58 |
| 15 | GLM-5.2 | 68.52 | #73 |
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-function-calling · How It Works · Data refreshed daily, snapshot 2026-10-20.