otter2.1 Benchmark Results

otter2.1: benchmark results

Provider: Other. Access: Open.

Unified ELO 1310 ± 18, rank #2422 of 2656 rated models, from 10 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM - Ko-GPQA-Diamond	23.74	Normalized accuracy (%)	55.6
Open Korean LLM - KorNAT-CKA	22.95	Normalized accuracy (%)	41.7
Open Korean LLM - Ko-EQ-Bench	0	EQ-Bench score	24.5
Open Korean LLM - Ko-GSM8K (flexible extract)	4.78	Exact match, flexible extract (%)	23.4
Open Korean LLM - KorNAT-Helpful	42.93	Normalized accuracy (%)	19.7
Open Korean LLM - Ko-Winogrande	53.83	Accuracy (%)	14.2
Open Korean LLM - KorNAT-Harmless	59.95	Normalized accuracy (%)	10.7
Open Ko-LLM Leaderboard	28.47	Average (%)	6.5
Open Korean LLM Leaderboard	28.47	Average Score (%)	6.5
Open Korean LLM - Ko-IFEval	1.38	Strict accuracy, prompt/instruction mean (%)	3.4

Interactive version: theaggregate.ai/model?slug=otter2-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.