N3N_gemma-2-9B-it_20241029_1532: benchmark results
Jikji Labs' (nhyha) fine-tune of Gemma 2 9B Instruct on arXiv-derived data, targeting mathematical reasoning and problem-solving. Provider: Other. Released 2024-10-29. Access: Open.
Unified ELO 1509 ± 1, rank #659 of 1392 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 16.39 | Score | 85.7 |
| Open LLM Leaderboard - GPQA | 12.08 | Score | 84.6 |
| Open LLM Leaderboard - BBH | 40.99 | Score | 80 |
| Open LLM Leaderboard - IFEval | 67.52 | Score | 80 |
| Open LLM Leaderboard - MMLU-Pro | 34.69 | Score | 75 |
| Open LLM Leaderboard - MATH Level 5 | 21.22 | Score | 73.1 |
| UGI - Writing | 29.18 | Writing Score | 34.1 |
| UGI - Natural Intelligence | 13.79 | NatInt Score | 13.9 |
| UGI - Willingness (W/10) | 1 | W/10 Score | 2.2 |
| UGI Leaderboard | 8.89 | UGI Score | 2 |
Interactive version: theaggregate.ai/model?slug=n3n-gemma-2-9b-it-20241029-1532 · How It Works · Data refreshed daily, snapshot 2026-09-05.