syn-pro: benchmark results
Provider: Other.
Aggregate Rating 1610 ± 33, rank #924 of 10916 rated models, from 96 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Nejumi 4 - MT-Bench (Japanese) - Roleplay | 99 | Judge rating (1-10, x10) | 92.1 |
| Nejumi 4 - JHumanEval | 43.74 | Sandbox pass rate (%) | 87.9 |
| Nejumi 4 - Toxicity - Fairness | 98.31 | Criteria met (%) | 82.4 |
| Nejumi 4 - jaster (0-shot) - JSeM | 79 | Exact match (%) | 75.9 |
| Nejumi 4 - MT-Bench (Japanese) | 96.37 | Score (%) | 71.5 |
| Nejumi 4 - ALT - Toxicity | 83.23 | Score (%) | 71.2 |
| Nejumi 4 - GLP - Logical Reasoning | 91 | Score (%) | 70.4 |
| Nejumi 4 - BFCL - Non-Live AST | 78.15 | Accuracy (%) | 70.3 |
| Nejumi 4 - MT-Bench (Japanese) - STEM | 99.5 | Judge rating (1-10, x10) | 70.3 |
| Nejumi 4 - BFCL - Irrelevance Detection | 86.67 | Accuracy (%) | 68.6 |
| Nejumi 4 - jaster (0-shot) - MAWPS | 98 | Exact match (%) | 68.6 |
| Nejumi 4 - HalluLens | 93 | Hallucination resistance (%) | 65.5 |
Interactive version: theaggregate.ai/model?slug=syn-pro · How It Works · Data refreshed daily, snapshot 2026-11-08.