Completed / CodeSOTA execution on White

Inspect the measurement.

HuggingFaceTB/SmolLM2-360M-Instruct · ARC-Challenge · 28.1% accuracy

32-example subset · 32 scored examples. Sub-1B 32-example pilot; FP32, 1024-token input ceiling, mean answer-token log likelihood. Native masked-padding adapter uses unpadded row forwards. Compare only this cohort protocol.

Run ID / completed

2c30cf2ceb6a87338eb33d7b
17 Oct 2026, 02:47 UTC

Model revision

a10cc1512eabd3dde888204e902eca88bddb4951

Comparison scope

e14efec58a56b426d1075a48d781531cc86194c0ae545ccae25ab8c742c4cdfa

Evaluator SHA-256

5011da874931804d8f5159762d18d33b71feb02044d808b106cca5da28178509

Observed resources

1s elapsed · 1.48 GiB peak torch allocation
Dollar cost: not measured

Download evidence

result.json samples.jsonl environment.json evaluate.py manifest.json

Inspect individual examples

Read the recorded prediction, reference and outcome for each example.

Scored examples: 32
Passed: 9
Failed: 23
Metric: accuracy

Examples are downloaded only when requested. Search covers all loaded records; 25 examples are displayed per page. Download all examples · JSONL

Example evidence has not been loaded.