Benchmark Almanac

InternLM-XComposer2-4KHD-7B

InternLM-XComposer2-4KHD-7B.

Shanghai AI Lab Released 9 Apr 2024 Family InternLM-XComposer The lab's model card
10
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Shanghai AI Lab Apr 2024

InternLM-XComposer2-4KHD-7B

Open weights Small

No Epoch Capabilities Index score yet
  • OCRBench v2 33.9% #49 /65
  • VCR (Visual Caption Restoration) 12.9% #34 /42
  • MMBench-EN v1.1 77% #79 /178

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
MMBench-CN v1.1 76.1% #74 of 178 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
MMBench 80.2% #55 of 155 Official leaderboard
MMBench-EN v1.1 77% #79 of 178 Official leaderboard
MMStar 55.3% #79 of 173 Official leaderboard
CCBench (MMBench Chinese Culture) 47.1% #72 of 152 Official leaderboard
CharXiv 25% #54 of 77 Official leaderboard
OCRBench v2 33.9% #49 of 65 Official leaderboard
VCR (Visual Caption Restoration) 12.9% #34 of 42 Official leaderboard
MTVQA-Test 11.2% #15 of 18 Official leaderboard

Other

BenchmarkScoreRankSource
OpenVLM Leaderboard 58.8 #87 of 173 Official leaderboard