Completed / CodeSOTA execution on White

Inspect the measurement.

Qwen/Qwen2.5-1.5B · CommonsenseQA (validation) · 50.0% accuracy

32-example subset · 32 scored examples. Pilot subset, CodeSOTA batched-v2 execution. Separate scope from serial v1; unchanged prompt/tokenization/metric contracts.

Run ID / completed

1501461aea74f8f8f769be82
17 Oct 2026, 15:37 UTC

Model revision

8faed761d45a263340a0528343f099c05c9a4323

Comparison scope

f0998ace0736b4da3a3e3949ec0597035cf98f4c1796febce8344e4f727cc90a

Evaluator SHA-256

bc899fb160f6881408863cd8bcdf96102dd6d8b10559a5f781a8cd816103da77

Observed resources

2s elapsed · 2.92 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: 16
Failed: 16
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.