AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
Model reports
BabyVision
Multimodal vision benchmark. Temperature=1.0, top_p=0.95, max context 164K tokens. Images resized to shorter side at least 1.5K pixels.
Evaluation context and evidence
- Source
- Model reports
- Publisher
- Not recorded
- Benchmark release
- 2025-12-01
- Collected
- Not recorded
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 1
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| GLM-5.3-Flash | 53.4 | percent | temp 1.0, top_p 0.95, max context 164K, images resized so shorter side >= 1.5K pixels | 2026-08-27 · document_publication | GLM-5.3-Flash |