Benchmark Almanac

llava-v1.5-7b

llava-v1.5-7b.

Released October 5th, 2023 Compare with others
23
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab Oct 2023

llava-v1.5-7b

No Epoch Capabilities Index score yet
  • MM-Vet 32.9% #145 /164
  • SEED-Bench-2-Plus 41.3% #127 /136
  • CoreCognition 48.5% #99 /119

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 43.9% #169 of 178 Official leaderboard

Professional work

BenchmarkScoreRankSource
GMAI-MMBench 38% #6 of 13 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
MMIU 19.2% #7 of 10 Official leaderboard
MIRB 28.5% #5 of 7 Official leaderboard
MMBench 66.5% #126 of 155 Official leaderboard
A-Bench 65.6% #95 of 116 Official leaderboard
ScienceQA 66.8% #14 of 17 Claim in VisionLLM v2: An End-to-End Generalist Multimodal Large L…, via Epoch AI
CoreCognition 48.5% #99 of 119 Official leaderboard
MMBench-EN v1.1 62.3% #154 of 178 Official leaderboard
MuirBench 23.5% #7 of 8 Official leaderboard
VCR (Visual Caption Restoration) 10.4% #37 of 42 Official leaderboard
MM-Vet 32.9% #145 of 164 Official leaderboard
LongVideoBench 40.4% #21 of 23 Official leaderboard
SpaCE-10 30.7% #33 of 36 Official leaderboard
CCBench (MMBench Chinese Culture) 17.8% #141 of 152 Official leaderboard
SEED-Bench-2-Plus 41.3% #127 of 136 Official leaderboard
MMStar 33.1% #166 of 173 Official leaderboard
MATH-Vision (MathVision) 8.52% #105 of 105 Official leaderboard
MMT-Bench 49.5% #15 of 15 Official leaderboard
BLINK 38% #11 of 11 Official leaderboard
DynaMath 16.6% #11 of 11 Official leaderboard
3DSRBench 36.8% #4 of 4 Official leaderboard

Other

BenchmarkScoreRankSource
OpenVLM Leaderboard 36.9 #165 of 173 Official leaderboard