Benchmark Almanac

LLaVA-OneVision 7B

LLaVA-OneVision 7B ranks first on StreamingBench.

ByteDance Seed Released August 6th, 2024 Family LLaVA-OneVision The lab's model card Compare with others
52
Benchmarks with a score
1
Ranked first, out of five or more models
6
In the top three
ByteDance Seed Aug 2024

LLaVA-OneVision 7B

Open weights Small

No Epoch Capabilities Index score yet
  • WorldSense (omnimodal) 37.7% #8 /12
  • Video SimpleQA 19.3% #20 /27
  • VideoReasonBench 0.30% #12 /14

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 80.9% #41 of 178 Official leaderboard
Video SimpleQA 19.3% #20 of 27 Official leaderboard
Creation-MMBench -43.49 #17 of 19 Official leaderboard
MM-IFEval 34% #9 of 9 Official leaderboard

Math and science

BenchmarkScoreRankSource
PhyX 5.70% #9 of 10 Official leaderboard

Coding

BenchmarkScoreRankSource
HumanEval-V 5.10% #18 of 24 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
MMBench 83.2% #31 of 155 Official leaderboard
StreamingBench 56.4% #1 of 5 Official leaderboard
MMBench-EN v1.1 80.9% #46 of 178 Official leaderboard
A-Bench 75.2% #32 of 116 Official leaderboard
MMStar 61.9% #48 of 173 Official leaderboard
MindCube 47.4% #2 of 7 Official leaderboard
CCBench (MMBench Chinese Culture) 54.9% #52 of 152 Official leaderboard
SpaCE-10 45.2% #13 of 36 Official leaderboard
xMMMU 41% #2 of 5 Official leaderboard
SEED-Bench-2-Plus 65.4% #55 of 136 Official leaderboard
OVBench 49.5% #3 of 7 Official leaderboard
OmniBench 47% #7 of 16 Official leaderboard
VSI-Bench 32.4% #4 of 9 Official leaderboard
MM-Vet 51.9% #80 of 164 Official leaderboard
DREAM-1K 31.7% #4 of 8 Official leaderboard
SITE 30.2% #3 of 6 Official leaderboard
OVO-Bench 52.7% #1 of 2 Official leaderboard
VLADBench 50% #4 of 7 Official leaderboard
TemporalBench 18.7% #6 of 10 Official leaderboard
ODV-Bench 51.6% #3 of 5 Official leaderboard
LEGO-Puzzles 33.6% #10 of 16 Official leaderboard
TOMATO 25.5% #14 of 22 Official leaderboard
ERQA 34.4% #11 of 17 Official leaderboard
KRETA 54% #11 of 17 Official leaderboard
MMMU 48.8% #89 of 136 Official leaderboard
We-Math 23.1% #14 of 21 Official leaderboard
WorldSense (omnimodal) 37.7% #8 of 12 Official leaderboard
VCR-Bench 30.7% #6 of 9 Official leaderboard
CharXiv (DQ) 48.7% #50 of 67 Official leaderboard
CausalVQA 45.3% #3 of 4 Official leaderboard
MEGA-Bench 23.9% #17 of 22 Official leaderboard
MMVU 37.9% #22 of 28 Official leaderboard
CharXiv 23.6% #61 of 77 Official leaderboard
VisualPuzzles 29.4% #23 of 29 Official leaderboard
LongDocURL 25% #4 of 5 Official leaderboard
MMMU-Pro 24.1% #48 of 57 Official leaderboard
VideoReasonBench 0.30% #12 of 14 Official leaderboard
Video-MMMU 33.9% #21 of 24 Official leaderboard
MMSI-Bench 24.5% #27 of 28 Official leaderboard
Point-Bench 6.32% #17 of 17 Official leaderboard
MME-CoT 30.9% #10 of 10 Official leaderboard
ViewSpatial-Bench 27.5% #7 of 7 Official leaderboard
OST-Bench 40.4% #6 of 6 Official leaderboard
VSI-Bench-Debiased 29.6% #4 of 4 Official leaderboard

Safety and security

BenchmarkScoreRankSource
Video-SafetyBench 2.70 #12 of 15 Official leaderboard

Other

BenchmarkScoreRankSource
OpenVLM Leaderboard 60.2 #82 of 173 Official leaderboard