InternLM-Chat-7B: benchmark results

Provider: Shanghai AI Lab. Access: Open.

Unified ELO 1375 ± 26, rank #2086 of 2656 rated models, from 17 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
SALAD-Bench Base95.52Safety Score (%)75.8
SALAD-Bench58.86Average Safety Score (%)72.7
SALAD-Bench Attack22.2Safety Score (%)69.7
SuperCLUE53.91Total Score57.9
InfiBench34.86Score (%)41
LLMEval-Fair - History4.03Discipline Score (0-10)13.8
AlignBench36.5Score (%)12.5
LLMEval-Fair - Literature3.17Discipline Score (0-10)12.1
LLMEval-Fair - Law5.57Discipline Score (0-10)10.3
LLMEval-Fair - Engineering2.63Discipline Score (0-10)8.6
LLMEval-Fair - Medicine3.13Discipline Score (0-10)8.6
LLMEval-Fair - Education4.87Discipline Score (0-10)6.9

Interactive version: theaggregate.ai/model?slug=internlm-chat-7b · How It Works · Data refreshed daily, snapshot 2026-09-19.