Embeddings / STS Benchmark
Sentence similarity
Two sentences → semantic similarity
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 · spearman higher is better. No global SOTA claim.
| System | Score | Samples | Elapsed¹ | Evidence |
|---|---|---|---|---|
| sentence-transformers/all-MiniLM-L6-v2 1110a243fdf4 | 0.924 | 32 | 1s | Inspect run → 16 Oct 2026, 23:28 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
sentence-transformers/stsb / test
Immutable dataset revision
ab7a5ac0e35aa22088bdcf23e7fd99b220e53308Upstream license metadata
See upstream terms · consult upstream terms
Protocol
codesota-pilot-v1 / similarity
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 32.6. Interest changes execution order, within the approved baseline list.
| System | Status |
|---|---|
| sentence-transformers/all-MiniLM-L6-v2 | completed |