SeaLLM-7B-v2 Benchmark Results

SeaLLM-7B-v2 — benchmark results

Provider: Sea AI Lab. Released 2024-01-29. Access: Open.

Unified ELO 1372 ± 12, rank #1335 of 1776 rated models, from 15 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM Leaderboard	495.16	Average Score (%)	87
Open LLM Leaderboard - MuSR	9.37	Score	45.4
Open LLM Leaderboard - BBH	27.44	Score	43.7
Open LLM Leaderboard - MATH Level 5	8.53	Score	42.8
Open LLM Leaderboard - MMLU-Pro	23.14	Score	39.3
Open Chinese LLM - ARC Challenge	48.72	Accuracy (%)	36.1
Open Chinese LLM - GSM8K	38.59	Accuracy (%)	35.9
Open LLM Leaderboard - IFEval	36.71	Score	35.3
Open Chinese LLM - TruthfulQA MC	52.13	Accuracy (%)	34.3
Open LLM Leaderboard - GPQA	3.8	Score	33.5
Open Chinese LLM - HellaSwag	56.44	Accuracy (%)	30
Open Chinese LLM - CMMLU	47.23	Accuracy (%)	24.8

Interactive version: theaggregate.ai/model?slug=seallm-7b-v2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.