Complete run of the Decision Index suite (edition 0.2; complete under 0.2.1) for
Hopper (G) 1.2 (revision d60a1d6), in the kit's compact
results.jsonl format (no request payloads). Scored with
apolinario/decision-index at 87d4650: Decision Index 0.2.1
40.77 (raw 55.23). See runs/hopper-g-1.2/environment.json for code, weights, hardware and hashes.
These are model outputs only; the benchmark texts are not included. The suite's upstream licences apply to the benchmarks themselves.
Complete run of the Decision Index suite (edition 0.2; complete under 0.2.1) for
Hopper (G) 1.2 (revision d60a1d6), in the kit's compact
results.jsonl format (no request payloads). Scored with
apolinario/decision-index at 87d4650: Decision Index 0.2.1
40.77 (raw 55.23). See runs/hopper-g-1.2/environment.json for code, weights, hardware and hashes.
These are model outputs only; the benchmark texts are not included. The suite's upstream licences apply to the benchmarks themselves.
