MT-Merge6-gemma-2-9B: benchmark results
zelk12's SLERP merge of two of his own Gemma 2 9B merge variants (MT-Merge6-UW and -CN), part of a long-running experimental merge series. Provider: zelk12. Released 2025-02-13. Access: Open.
Aggregate Rating 1503 ± 49, rank #2296 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - BBH | 59.49 | Score | 81 |
| Open LLM Leaderboard - GPQA | 32.89 | Score | 80.1 |
| Open LLM Leaderboard - MMLU-Pro | 41.15 | Score | 74.8 |
| UGI - Willingness (W/10) | 7 | W/10 Score | 70.9 |
| UGI Leaderboard | 38.75 | UGI Score | 61.4 |
| Open LLM Leaderboard - MuSR | 40.98 | Score | 50.2 |
| Open LLM Leaderboard - MATH Level 5 | 8.01 | Score | 40.9 |
| UGI - Writing | 29.17 | Writing Score | 33.3 |
| UGI - Natural Intelligence | 15.18 | NatInt Score | 19 |
| Open LLM Leaderboard - IFEval | 16.95 | Score | 7.8 |
Interactive version: theaggregate.ai/model?slug=mt-merge6-gemma-2-9b · How It Works · Data refreshed daily, snapshot 2026-11-08.