cogvlm2-llama3-chat-19B: benchmark results
Provider: Zhipu.
Aggregate Rating 1419 ± 45, rank #5300 of 10489 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CoreCognition Image only Intuitivephysics | 68.1 | Accuracy (%) | 100 |
| CoreCognition Image only Permanence | 78.13 | Accuracy (%) | 92.8 |
| CoreCognition Image only Perspective | 43.66 | Accuracy (%) | 79.6 |
| CoreCognition Image only Boundary | 76.31 | Accuracy (%) | 77.6 |
| CoreCognition Image only Mean | 60.08 | Accuracy (%) | 76.3 |
| CoreCognition Image only Continuity | 61.72 | Accuracy (%) | 57.9 |
| CoreCognition Image only Perceptualconstancy | 60.37 | Accuracy (%) | 56.6 |
| CapArena-Auto | -8.5 | CapArena-Auto Score (avg) | 52.4 |
| CapArena-Auto vs CogVLM-19B | 0 | CapArena-Auto Score (vs CogVLM-19B) | 52.4 |
| CapArena-Auto vs MiniCPM-8B | 31 | CapArena-Auto Score (vs MiniCPM-8B) | 52.4 |
| CoreCognition Image only Intentionality | 65.71 | Accuracy (%) | 50 |
| CoreCognition Image only Toolusing | 92.29 | Accuracy (%) | 49.3 |
Interactive version: theaggregate.ai/model?slug=cogvlm2-llama3-chat-19b · How It Works · Data refreshed daily, snapshot 2026-11-20.