Benchmark Almanac

InternVL2-40B

InternVL2-40B places in the top three on 2 benchmarks.

Shanghai AI Lab Released July 8th, 2024 Compare with others
22
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
Shanghai AI Lab Jul 2024

InternVL2-40B

Open weights

No Epoch Capabilities Index score yet
  • MM-IFEval 45% #5 /9
  • MM-Vet 61.8% #48 /164
  • SEED-Bench-2-Plus 69.2% #21 /136

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 84.9% #17 of 178 Official leaderboard
MM-IFEval 45% #5 of 9 Official leaderboard

Math and science

BenchmarkScoreRankSource
OlympicArena 20% #15 of 25 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
CCBench (MMBench Chinese Culture) 80.2% #8 of 152 Official leaderboard
MMBench 86.8% #11 of 155 Official leaderboard
MMBench-EN v1.1 85.1% #17 of 178 Official leaderboard
OmniBench 54.3% #2 of 16 Official leaderboard
VCR (Visual Caption Restoration) 47.5% #6 of 42 Official leaderboard
SEED-Bench-2-Plus 69.2% #21 of 136 Official leaderboard
CoreCognition 61% #22 of 119 Official leaderboard
MMStar 64.7% #34 of 173 Official leaderboard
A-Bench 75.2% #31 of 116 Official leaderboard
TOMATO 29% #6 of 22 Official leaderboard
MM-Vet 61.8% #48 of 164 Official leaderboard
VSI-Bench 37% #3 of 9 Official leaderboard
LongVideoBench 60.6% #8 of 23 Official leaderboard
DynaMath 41.8% #5 of 11 Official leaderboard
MMMU 55.2% #73 of 136 Official leaderboard
MMMU-Pro 34.2% #40 of 57 Official leaderboard
LVBench 39.6% #7 of 9 Official leaderboard
MotionBench 54% #11 of 12 Official leaderboard

Other

BenchmarkScoreRankSource
OpenVLM Leaderboard 69.7 #38 of 173 Official leaderboard