Benchmark Almanac

InternVL-Chat-V1-5

InternVL-Chat-V1-5.

Released 18 Apr 2024
13
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab Apr 2024

InternVL-Chat-V1-5

No Epoch Capabilities Index score yet
  • A-Bench 71.7% #60 /116
  • VCR (Visual Caption Restoration) 25.7% #17 /42
  • OlympicArena 17.4% #21 /25

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 79.1% #56 of 178 Official leaderboard

Math and science

BenchmarkScoreRankSource
OlympicArena 17.4% #21 of 25 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
CCBench (MMBench Chinese Culture) 69.8% #26 of 152 Official leaderboard
MMBench 82.3% #36 of 155 Official leaderboard
MMBench-EN v1.1 80.3% #51 of 178 Official leaderboard
MME 1637.8 #6 of 16 Official leaderboard
MMStar 57.1% #69 of 173 Official leaderboard
VCR (Visual Caption Restoration) 25.7% #17 of 42 Official leaderboard
A-Bench 71.7% #60 of 116 Official leaderboard
CharXiv 29.2% #45 of 77 Official leaderboard
MTVQA-Test 14.9% #14 of 18 Official leaderboard
Video-MME 52.4% #22 of 26 Official leaderboard

Other

BenchmarkScoreRankSource
OpenVLM Leaderboard 61.9 #73 of 173 Official leaderboard