AnFeng_v3.1-Avocet: benchmark results
NLPark's sparsely documented 34B conversational model on the Yi-34B architecture, tagged not-for-all-audiences. Provider: Other. Released 2024-08-03. Access: Open.
Unified ELO 1492 ± 1, rank #816 of 1553 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MMLU-Pro | 38.2 | Score | 82.3 |
| Open LLM Leaderboard - MuSR | 14.98 | Score | 81 |
| Open LLM Leaderboard - BBH | 40.31 | Score | 79.4 |
| Open LLM Leaderboard - GPQA | 9.96 | Score | 78 |
| Open LLM Leaderboard - MATH Level 5 | 15.94 | Score | 63.7 |
| Open LLM Leaderboard - IFEval | 50.96 | Score | 60.8 |
| Open Korean LLM Leaderboard | 36.8 | Average Score (%) | 56 |
Interactive version: theaggregate.ai/model?slug=anfeng-v3-1-avocet · How It Works · Data refreshed daily, snapshot 2026-09-08.