llm-jp-4.1-33B: benchmark results
Provider: National Institute of Informatics. Released 2026-09-28. Access: Open.
Aggregate Rating 1679 ± 15, rank #247 of 1647 rated models, from 136 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM-jp4.1 Release Swallow - AIME 2025 @1 | 0.76 | Pass@1 (0–1) | 100 |
| LLM-jp4.1 Release Swallow - GPQA Diamond @1 | 0.69 | Pass@1 (0–1) | 100 |
| LLM-jp4.1 Release Swallow - HumanEval+ @1 | 0.94 | Pass@1 (0–1) | 100 |
| LLM-jp4.1 Release Swallow - JGPQA Diamond | 0.68 | Score (0–1) | 100 |
| LLM-jp4.1 Release Swallow - JHumanEval @1 | 0.94 | Pass@1 (0–1) | 100 |
| LLM-jp4.1 Release Swallow - MCLM Math 100 @1 | 0.97 | Pass@1 (0–1) | 100 |
| LLM-jp4.1 Release Swallow - MCLM Math 100 @4 | 0.99 | Pass@4 (0–1) | 100 |
| LLM-jp4.1 Release Swallow - MMLU-ProX EN | 0.79 | Score (0–1) | 100 |
| LLM-jp4.1 Release Swallow - Math 500 | 0.98 | Score (0–1) | 100 |
| LLM-jp4.1 Release Swallow - Polymath JA high | 0.6 | Score (0–1) | 100 |
| LLM-jp4.1 Release Swallow - Polymath JA top | 0.3 | Score (0–1) | 100 |
| Open Japanese LLM v2 - JBLiMP | 85.8 | Accuracy (%) | 100 |
Interactive version: theaggregate.ai/model?slug=llm-jp-4-1-33b · How It Works · Data refreshed daily, snapshot 2026-10-17.