Molmo-72B
Molmo-72B places in the top three on Point-Bench.
9
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Ai2 Sep 2024 Molmo-72B
Open weights Flagship
No Epoch Capabilities Index score yet
- HumanEval-V 3.20% #15 /24
- Point-Bench 63.8% #2 /17
- MMBench-EN v1.1 79.4% #60 /178
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 | 79.6% | #47 of 178 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HumanEval-V | 3.20% | #15 of 24 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Point-Bench | 63.8% | #2 of 17 | Official leaderboard | |
| MMStar | 63.3% | #41 of 173 | Official leaderboard | |
| MMBench-EN v1.1 | 79.4% | #60 of 178 | Official leaderboard | |
| CharXiv | 36.5% | #30 of 77 | Official leaderboard | |
| Vision Arena | 1,045 | #121 of 136 | Official leaderboard | |
| VQAv2 | 86.7% | #2 of 2 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 64.0 | #66 of 173 | Official leaderboard |