LLaVA-1.6-13B: benchmark results
Provider: LLaVA Team.
Aggregate Rating 1414 ± 36, rank #5446 of 10916 rated models, from 33 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AICA-Bench - Emotion Reasoning | 73.57 | Emotion reasoning score on a percent scale: the model explai | 68.2 |
| HELM Image2Struct - Image2Musicsheet | 25.85 | EMS | 63.2 |
| LabRobFail-Bench - Failure Detection | 52.96 | Top-1 accuracy (%; binary detection of whether the trajector | 50 |
| LabRobFail-Bench - Task Understanding | 35.8 | Top-1 accuracy (%; decomposing the video into its atomic lab | 50 |
| LabRobFail-Bench - Temporal Localization | 13.24 | Top-1 accuracy (%; the frame at which the failure occurs; ro | 50 |
| CHOICE | 0.59 | Overall Score | 43.5 |
| HELM Image2Struct - Image2Webpage Css | 49.01 | EMS | 36.8 |
| AICA-Bench - Emotion-Guided Generation | 64.51 | Emotion-guided content generation score on a percent scale: | 31.8 |
| HELM Image2Struct - Image2Latex Wild | 34.86 | EMS | 31.6 |
| HELM Image2Struct - Image2Webpage | 44.7 | EMS | 31.6 |
| HELM Image2Struct - Image2Webpage Javascript | 44.85 | EMS | 31.6 |
| HELM Image2Struct - Core Scenarios | 31.58 | Mean win rate | 26.3 |
Interactive version: theaggregate.ai/model?slug=llava-1-6-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.