gte-Qwen2-7B-instruct: benchmark results
Provider: Alibaba. Released 2024-06-15. Access: Open.
Aggregate Rating 1334 ± 49, rank #8090 of 10916 rated models, from 16 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| PL-MTEB | 65.86 | Mean Main Score (%) | 100 |
| Open Korean LLM - KorNAT-Harmless | 64.27 | Normalized accuracy (%) | 72.1 |
| Open Korean LLM - KorNAT-CKA | 25 | Normalized accuracy (%) | 54.4 |
| Open LLM Leaderboard - MMLU-Pro | 33.21 | Score | 46.8 |
| Open LLM Leaderboard - MATH Level 5 | 6.42 | Score | 34.9 |
| Open LLM Leaderboard - BBH | 44.95 | Score | 33.8 |
| Open Korean LLM - KorNAT-Helpful | 44.98 | Normalized accuracy (%) | 33.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 6.75 | Exact match, flexible extract (%) | 28.7 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-Winogrande | 55.56 | Accuracy (%) | 21.1 |
| Open Korean LLM - Ko-IFEval | 20.66 | Strict accuracy, prompt/instruction mean (%) | 19.4 |
| Open Korean LLM Leaderboard | 30.46 | Average Score (%) | 19.3 |
Interactive version: theaggregate.ai/model?slug=gte-qwen2-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.