Einstein-v7-Qwen2-7B: benchmark results
Weyaxi's science-focused full fine-tune of Qwen2 7B, trained on ~40 datasets spanning physics, chemistry, biology, and math in ChatML format. Provider: Other. Released 2024-06-24. Access: Open.
Unified ELO 1531 ± 1, rank #603 of 1553 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM Leaderboard | 45.25 | Average Score (%) | 91.4 |
| Open LLM Leaderboard - MuSR | 14.06 | Score | 77 |
| Open LLM Leaderboard - MMLU-Pro | 34.4 | Score | 74.7 |
| Open LLM Leaderboard - MATH Level 5 | 19.94 | Score | 70.8 |
| Open LLM Leaderboard - BBH | 32.84 | Score | 63.3 |
| Open LLM Leaderboard - GPQA | 6.6 | Score | 55.6 |
| Open LLM Leaderboard - IFEval | 41 | Score | 41.3 |
Interactive version: theaggregate.ai/model?slug=einstein-v7-qwen2-7b · How It Works · Data refreshed daily, snapshot 2026-09-08.