Vision / CIFAR-10
Image classification
Image → one of ten object classes
Model size vs score
1 compatible measurements. Parameter counts come from the architecture instantiated from each pinned model configuration; no weights are loaded for this count. Click a point to inspect its evidence.
Measured results
Pilot comparison · first 32 valid examples · accuracy higher is better. No global SOTA claim.
| System | Score | Samples | Elapsed¹ | Evidence |
|---|---|---|---|---|
| openai/clip-vit-base-patch32 3d74acf9a28c | 93.8% | 32 | 2s | Inspect run → 16 Oct 2026, 23:29 UTC |
¹ Evaluation elapsed time includes model loading after dataset selection. It is not serving latency or a fair speed comparison.
What this measures
Benchmark origin
Dataset / split
uoft-cs/cifar10 / test
Immutable dataset revision
0b2714987fa478483af9968de7c934580d0bb9a2Upstream license metadata
unknown · consult upstream terms
Protocol
codesota-pilot-v1 / vision
Selection
First 32 valid examples in the pinned split order. SNLI rows without a valid label are excluded.
Configuration
Seed 42. Greedy generation for math and code. Mean answer-token log likelihood for text classification, completion and declarative multiple-choice recipes. No model judge.
Planned runs
0 qualified visits in 30 days · priority 35.1. Interest changes execution order, within the approved baseline list.
| System | Status |
|---|---|
| openai/clip-vit-base-patch32 | completed |