bionemo-codonfm-score: worth installing? Reported results

Reported results for bionemo-codonfm-score (NVIDIA/skills) from NVIDIA, one row per receipt, in plain words.

Skill skills/bionemo-codonfm-score in NVIDIA/skills.

One row per receipt. No figure on this page combines two rows.

Reported by: Reported by NVIDIA in its benchmark card
Model: Claude Opus 5 (aws/anthropic/bedrock-claude-opus-5, as the source names it)
Harness: claude-code, version not stated
Date: 2026-10-07
Tasks and runs: 3 tasks, as printed
Result: NVIDIA reported a score of 96.1% overall and no uplift figure (1 attempt per task). Overall: 96.1% — baseline ran, but no comparable score was available; uplift unavailable Security: 100.0% → 100.0% (±0.0 points) Correctness: 100.0% → 100.0% (±0.0 points) Discoverability: 95.0% — baseline ran, but no comparable score was available; uplift unavailable Effectiveness: 90.0% → 93.3% (+3.3 points) Efficiency: 92.1% — baseline ran, but no comparable score was available; uplift unavailable
Tokens: 1,308,984 tokens with the skill and 3,855,619 without, over all cases, as printed; the card gives no cost
Freshness: Reported on Opus 5. The registry lists no opus model released after this run, as of the build date.
Skill commit: 14a98ae278cec7e867695189d0f4003c08e4f765
Receipt: codonfm-score-aws-anthropic-bedrock-claude-opus-5-imported-nvidia-cards-claude-code-2026-10-07-18147b1abc3a.json

Reported by: Reported by NVIDIA in its benchmark card
Model: GPT-5.5 (openai/openai/gpt-5.5, as the source names it)
Harness: codex, version not stated
Date: 2026-10-07
Tasks and runs: 3 tasks, as printed
Result: NVIDIA reported a score of 84.8% overall and no uplift figure (1 attempt per task). Overall: 84.8% — baseline ran, but no comparable score was available; uplift unavailable Security: 33.3% → 66.7% (+33.4 points) Correctness: 100.0% → 100.0% (±0.0 points) Discoverability: 80.0% — baseline ran, but no comparable score was available; uplift unavailable Effectiveness: 90.0% → 96.7% (+6.7 points) Efficiency: 80.7% — baseline ran, but no comparable score was available; uplift unavailable
Tokens: 1,491,127 tokens with the skill and 1,204,536 without, over all cases, as printed; the card gives no cost
Freshness: Reported on GPT-5.5. Freshness unknown: the registry has no release date for it.
Skill commit: 14a98ae278cec7e867695189d0f4003c08e4f765
Receipt: codonfm-score-openai-openai-gpt-5-5-imported-nvidia-cards-codex-2026-10-07-18147b1abc3a.json

Built on 2026-10-15 from committed receipts.