NVLM-D-72B
NVLM-D-72B places in the top three on VL-RewardBench.
16
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
NVLM-D-72B
Open weights Flagship
No Epoch Capabilities Index score yet
- ZeroBench 1.00% #70 /76
- MM-Vet 58.9% #57 /164
- SEED-Bench-2-Plus 68.4% #27 /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
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMBench-CN v1.1 | 78% | #61 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CoreCognition | 66% | #4 of 119 | Official leaderboard | |
| SEED-Bench-2-Plus | 68.4% | #27 of 136 | Official leaderboard | |
| MMStar | 63.7% | #39 of 173 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 59% | #42 of 152 | Official leaderboard | |
| MMBench | 80.4% | #53 of 155 | Official leaderboard | |
| MM-Vet | 58.9% | #57 of 164 | Official leaderboard | |
| MMBench-EN v1.1 | 79% | #62 of 178 | Official leaderboard | |
| VL-RewardBench | 44.1% | #3 of 8 | Official leaderboard | |
| CharXiv | 36.8% | #29 of 77 | Official leaderboard | |
| MMMU | 59.7% | #56 of 136 | Official leaderboard | |
| CharXiv (DQ) | 63.9% | #29 of 67 | Official leaderboard | |
| A-Bench | 72.1% | #59 of 116 | Official leaderboard | |
| MEGA-Bench | 25.6% | #14 of 22 | Official leaderboard | |
| ZeroBench | 1.00% | #70 of 76 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 67.6 | #46 of 173 | Official leaderboard |