rewirebio.iobenchmarks
Dataset subset

BenchBench-Cloning construct-design tasks with a rubric model judge (10)

The ten construct-design tasks whose final score is the product of a deterministic grader's result and a rubric-based model judge's score of the written reasoning and construction plan.

Evaluation results

80 evaluations · 80 results. Different protocols are not a single leaderboard.

Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: Claude Mythos 5.1 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: AG/AP1 chimera plasmid
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
1/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Mythos 5.1 on BenchBench-Cloning construct design: AG/AP1 chimera plasmid

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'AG/AP1 chimera plasmid', column 'Claude Mythos 5.1'
Configuration: Claude Mythos 5.1 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Alkaloid-pathway GoldenBraid set
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Mythos 5.1 on BenchBench-Cloning construct design: Alkaloid-pathway GoldenBraid set

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Alkaloid-pathway GoldenBraid set', column 'Claude Mythos 5.1'
Configuration: Claude Mythos 5.1 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Detector choice from antibody data
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Mythos 5.1 on BenchBench-Cloning construct design: Detector choice from antibody data

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Detector choice from antibody data', column 'Claude Mythos 5.1'
Configuration: Claude Mythos 5.1 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: GFP into EcoFlex vector
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
1/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Mythos 5.1 on BenchBench-Cloning construct design: GFP into EcoFlex vector

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'GFP into EcoFlex vector', column 'Claude Mythos 5.1'
Configuration: Claude Mythos 5.1 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Insulin intermediate construct
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Mythos 5.1 on BenchBench-Cloning construct design: Insulin intermediate construct

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Insulin intermediate construct', column 'Claude Mythos 5.1'
Configuration: Claude Mythos 5.1 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Insulin two-chain constructs
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Mythos 5.1 on BenchBench-Cloning construct design: Insulin two-chain constructs

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Insulin two-chain constructs', column 'Claude Mythos 5.1'
Configuration: Claude Mythos 5.1 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Minimal-edit recoding
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Mythos 5.1 on BenchBench-Cloning construct design: Minimal-edit recoding

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Minimal-edit recoding', column 'Claude Mythos 5.1'
Configuration: Claude Mythos 5.1 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Prime-assembly donor family
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Mythos 5.1 on BenchBench-Cloning construct design: Prime-assembly donor family

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Prime-assembly donor family', column 'Claude Mythos 5.1'
Configuration: Claude Mythos 5.1 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Synthetic-chromosome locus edit
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Mythos 5.1 on BenchBench-Cloning construct design: Synthetic-chromosome locus edit

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Synthetic-chromosome locus edit', column 'Claude Mythos 5.1'
Configuration: Claude Mythos 5.1 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Tus/TerB HEK293 constructs
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
1/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Mythos 5.1 on BenchBench-Cloning construct design: Tus/TerB HEK293 constructs

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Tus/TerB HEK293 constructs', column 'Claude Mythos 5.1'
Configuration: Claude Opus 5.5 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: AG/AP1 chimera plasmid
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
1/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Opus 5.5 on BenchBench-Cloning construct design: AG/AP1 chimera plasmid

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'AG/AP1 chimera plasmid', column 'Claude Opus 5.5'
Configuration: Claude Opus 5.5 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Alkaloid-pathway GoldenBraid set
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Opus 5.5 on BenchBench-Cloning construct design: Alkaloid-pathway GoldenBraid set

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Alkaloid-pathway GoldenBraid set', column 'Claude Opus 5.5'
Configuration: Claude Opus 5.5 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Detector choice from antibody data
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Opus 5.5 on BenchBench-Cloning construct design: Detector choice from antibody data

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Detector choice from antibody data', column 'Claude Opus 5.5'
Configuration: Claude Opus 5.5 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: GFP into EcoFlex vector
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
3/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Opus 5.5 on BenchBench-Cloning construct design: GFP into EcoFlex vector

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'GFP into EcoFlex vector', column 'Claude Opus 5.5'
Configuration: Claude Opus 5.5 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Insulin intermediate construct
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Opus 5.5 on BenchBench-Cloning construct design: Insulin intermediate construct

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Insulin intermediate construct', column 'Claude Opus 5.5'
Configuration: Claude Opus 5.5 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Insulin two-chain constructs
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Opus 5.5 on BenchBench-Cloning construct design: Insulin two-chain constructs

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Insulin two-chain constructs', column 'Claude Opus 5.5'
Configuration: Claude Opus 5.5 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Minimal-edit recoding
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
1/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Opus 5.5 on BenchBench-Cloning construct design: Minimal-edit recoding

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Minimal-edit recoding', column 'Claude Opus 5.5'
Configuration: Claude Opus 5.5 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Prime-assembly donor family
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Opus 5.5 on BenchBench-Cloning construct design: Prime-assembly donor family

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Prime-assembly donor family', column 'Claude Opus 5.5'
Configuration: Claude Opus 5.5 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Synthetic-chromosome locus edit
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
1/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Opus 5.5 on BenchBench-Cloning construct design: Synthetic-chromosome locus edit

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Synthetic-chromosome locus edit', column 'Claude Opus 5.5'
Configuration: Claude Opus 5.5 in Claude Code 2.1.289, max reasoning effortTask: BenchBench-Cloning construct design: Tus/TerB HEK293 constructs
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Claude Opus 5.5 on BenchBench-Cloning construct design: Tus/TerB HEK293 constructs

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Tus/TerB HEK293 constructs', column 'Claude Opus 5.5'
Configuration: Gemini 3.8 Flash in Gemini CLI 0.63.0, high reasoning effortTask: BenchBench-Cloning construct design: AG/AP1 chimera plasmid
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
1/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Gemini 3.8 Flash on BenchBench-Cloning construct design: AG/AP1 chimera plasmid

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'AG/AP1 chimera plasmid', column 'Gemini 3.8 Flash'
Configuration: Gemini 3.8 Flash in Gemini CLI 0.63.0, high reasoning effortTask: BenchBench-Cloning construct design: Alkaloid-pathway GoldenBraid set
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Gemini 3.8 Flash on BenchBench-Cloning construct design: Alkaloid-pathway GoldenBraid set

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Alkaloid-pathway GoldenBraid set', column 'Gemini 3.8 Flash'
Configuration: Gemini 3.8 Flash in Gemini CLI 0.63.0, high reasoning effortTask: BenchBench-Cloning construct design: Detector choice from antibody data
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Gemini 3.8 Flash on BenchBench-Cloning construct design: Detector choice from antibody data

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Detector choice from antibody data', column 'Gemini 3.8 Flash'
Configuration: Gemini 3.8 Flash in Gemini CLI 0.63.0, high reasoning effortTask: BenchBench-Cloning construct design: GFP into EcoFlex vector
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
0/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Gemini 3.8 Flash on BenchBench-Cloning construct design: GFP into EcoFlex vector

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'GFP into EcoFlex vector', column 'Gemini 3.8 Flash'
Configuration: Gemini 3.8 Flash in Gemini CLI 0.63.0, high reasoning effortTask: BenchBench-Cloning construct design: Insulin intermediate construct
Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10)
5/5 Count (construct-design attempts passed out of 5 on one task at top reasoning effort, pass at a final score of at least 0.9; grading deterministic multiplied by a GPT-6 Astra rubric score, so the outcome depends on the judge; top reasoning tier, the highest of this system's three settings)
count · higher

Uncertainty: Not reported by the source: Table G2 prints no interval for the per-task counts.

Coverage: 5/5 attempts scored

Author-reported evaluation · Source checked
Methods, coverage and source

Gemini 3.8 Flash on BenchBench-Cloning construct design: Insulin intermediate construct

benchbench-cloning-20261106-protocol-construct-design-per-task-rubric-judged

Aggregation: Not reported

BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Insulin intermediate construct', column 'Gemini 3.8 Flash'

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-11-21-c8bea25e5abb · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified
  • Sample annotations are recorded: not yet verified
  • Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • A pinned run recipe exists: not yet verified
  • Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Independent validation data exist: not yet verified
  • Overlap with training data is checked: not yet verified

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Subset and evaluation context

This record describes a particular subset or cohort used in an evaluation. Its results do not describe the full dataset.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

11 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Eligible count
10
Context-only references
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1)

Original source ↗

Table A1, column 'Grading', rows 4 and 7 to 15

Version: arXiv v1, dated 23 October 2026
Retrieved: 2026-11-06T11:51:23Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.eligible_count

Source artifact SHA-256: 6f5044b1bbbd81ad86b23cb536e2cae6428e0d9126f11546041355518febdc39

Hash scope: Hash scope not separately documented; inspect source record

Archive member: artifacts/arxiv-2610.33355v1.layout.txt.gz

Limitations
2 values
  • GPT-6 Astra is the judge and is also one of the eight evaluated systems (Section 3.3).
  • Table F3 records that 34 of the 142 top-effort attempts that cleared the deterministic checks on these tasks were then scored below 0.9 by the judge.
Context-only references
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1)

Original source ↗

Table A1, column 'Grading', rows 4 and 7 to 15

Version: arXiv v1, dated 23 October 2026
Retrieved: 2026-11-06T11:51:23Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.limitations

Source artifact SHA-256: 6f5044b1bbbd81ad86b23cb536e2cae6428e0d9126f11546041355518febdc39

Hash scope: Hash scope not separately documented; inspect source record

Archive member: artifacts/arxiv-2610.33355v1.layout.txt.gz

Source dataset
benchbench-cloning-20261106-dataset-tasks
Context-only references
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1)

Original source ↗

Table A1, column 'Grading', rows 4 and 7 to 15

Version: arXiv v1, dated 23 October 2026
Retrieved: 2026-11-06T11:51:23Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.source_dataset

Source artifact SHA-256: 6f5044b1bbbd81ad86b23cb536e2cae6428e0d9126f11546041355518febdc39

Hash scope: Hash scope not separately documented; inspect source record

Archive member: artifacts/arxiv-2610.33355v1.layout.txt.gz

Source location
Table A1, column 'Grading', rows 4 and 7 to 15
Context-only references
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1)

Original source ↗

Table A1, column 'Grading', rows 4 and 7 to 15

Version: arXiv v1, dated 23 October 2026
Retrieved: 2026-11-06T11:51:23Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.source_locator

Source artifact SHA-256: 6f5044b1bbbd81ad86b23cb536e2cae6428e0d9126f11546041355518febdc39

Hash scope: Hash scope not separately documented; inspect source record

Archive member: artifacts/arxiv-2610.33355v1.layout.txt.gz

Split
Evaluation only
Context-only references
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1)

Original source ↗

Table A1, column 'Grading', rows 4 and 7 to 15

Version: arXiv v1, dated 23 October 2026
Retrieved: 2026-11-06T11:51:23Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.split

Source artifact SHA-256: 6f5044b1bbbd81ad86b23cb536e2cae6428e0d9126f11546041355518febdc39

Hash scope: Hash scope not separately documented; inspect source record

Archive member: artifacts/arxiv-2610.33355v1.layout.txt.gz

Subset scope
Tasks whose Table A1 grading column reads 'Deterministic + rubric judge': Detector choice from antibody data; AG/AP1 chimera plasmid; Synthetic-chromosome locus edit; Alkaloid-pathway GoldenBraid set; GFP into EcoFlex vector; Prime-assembly donor family; Tus/TerB HEK293 constructs; Minimal-edit recoding; Insulin two-chain constructs; Insulin intermediate construct
Context-only references
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1)

Original source ↗

Table A1, column 'Grading', rows 4 and 7 to 15

Version: arXiv v1, dated 23 October 2026
Retrieved: 2026-11-06T11:51:23Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.subset_scope

Source artifact SHA-256: 6f5044b1bbbd81ad86b23cb536e2cae6428e0d9126f11546041355518febdc39

Hash scope: Hash scope not separately documented; inspect source record

Archive member: artifacts/arxiv-2610.33355v1.layout.txt.gz

Version
As described in arXiv:2610.33355v1 Table A1
Context-only references
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1)

Original source ↗

Table A1, column 'Grading', rows 4 and 7 to 15

Version: arXiv v1, dated 23 October 2026
Retrieved: 2026-11-06T11:51:23Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.version

Source artifact SHA-256: 6f5044b1bbbd81ad86b23cb536e2cae6428e0d9126f11546041355518febdc39

Hash scope: Hash scope not separately documented; inspect source record

Archive member: artifacts/arxiv-2610.33355v1.layout.txt.gz

Description
The ten construct-design tasks whose final score is the product of a deterministic grader's result and a rubric-based model judge's score of the written reasoning and construction plan.
Context-only references
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1)

Original source ↗

Table A1, column 'Grading', rows 4 and 7 to 15

Version: arXiv v1, dated 23 October 2026
Retrieved: 2026-11-06T11:51:23Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: description

Source artifact SHA-256: 6f5044b1bbbd81ad86b23cb536e2cae6428e0d9126f11546041355518febdc39

Hash scope: Hash scope not separately documented; inspect source record

Archive member: artifacts/arxiv-2610.33355v1.layout.txt.gz

Relationship: same data as
benchbench-cloning-20261106-data-construct-design-tasks
Context-only references
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1)

Original source ↗

Table A1, column 'Grading', rows 4 and 7 to 15

Version: arXiv v1, dated 23 October 2026
Retrieved: 2026-11-06T11:51:23Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: links:same_data_as:benchbench-cloning-20261106-data-construct-design-tasks

Source artifact SHA-256: 6f5044b1bbbd81ad86b23cb536e2cae6428e0d9126f11546041355518febdc39

Hash scope: Hash scope not separately documented; inspect source record

Archive member: artifacts/arxiv-2610.33355v1.layout.txt.gz

Relationship: used in
benchbench-cloning-20261106-benchmark-construct-design
Context-only references
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1)

Original source ↗

Table A1, column 'Grading', rows 4 and 7 to 15

Version: arXiv v1, dated 23 October 2026
Retrieved: 2026-11-06T11:51:23Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: links:used_in:benchbench-cloning-20261106-benchmark-construct-design

Source artifact SHA-256: 6f5044b1bbbd81ad86b23cb536e2cae6428e0d9126f11546041355518febdc39

Hash scope: Hash scope not separately documented; inspect source record

Archive member: artifacts/arxiv-2610.33355v1.layout.txt.gz

How to read the evidence

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and record identifiers

Technical metadata for this record is tracked under stable ID benchbench-cloning-20261106-data-construct-design-rubric-judged.

Source locator: Table A1, column 'Grading', rows 4 and 7 to 15

Related records

Suggest a correction