Configuration: Claude Mythos 5.1 in Claude Code 2.1.289, max reasoning effort Task: 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 Evidence concern: excluded from comparisons Table D2's construct-design rate for Gemini 4 Argon at low effort, 31.9%, cannot be a mean of binary outcomes over the stated 15 tasks times 5 attempts: no integer numerator over 75 falls in its rounding window [23.8875, 23.9625], while all 23 other printed construct rates do. Its printed 95% interval [10.7, 52.0] is also byte-identical to the same system's top-effort interval. The two signals together indicate a transcription fault in the paper rather than a measured value, and the paper prints nothing that resolves it: the lane's aggregate is 15.8 under either 31.9 or 32.0, and Table G2's per-task solves are top-effort only. The printed value is kept as published and this entry withholds it from automatic comparison; the lane's other results are not covered.BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table D2, row 'Gemini 4 Argon' tier 'low' effort 'low', column 'Construct design % [95% CI]'
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 Opus 5.5 in Claude Code 2.1.289, max reasoning effort Task: 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 Evidence concern: excluded from comparisons Table D2's construct-design rate for Gemini 4 Argon at low effort, 31.9%, cannot be a mean of binary outcomes over the stated 15 tasks times 5 attempts: no integer numerator over 75 falls in its rounding window [23.8875, 23.9625], while all 23 other printed construct rates do. Its printed 95% interval [10.7, 52.0] is also byte-identical to the same system's top-effort interval. The two signals together indicate a transcription fault in the paper rather than a measured value, and the paper prints nothing that resolves it: the lane's aggregate is 15.8 under either 31.9 or 32.0, and Table G2's per-task solves are top-effort only. The printed value is kept as published and this entry withholds it from automatic comparison; the lane's other results are not covered.BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table D2, row 'Gemini 4 Argon' tier 'low' effort 'low', column 'Construct design % [95% CI]'
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: Gemini 3.8 Flash in Gemini CLI 0.63.0, high reasoning effort Task: 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 Evidence concern: excluded from comparisons Table D2's construct-design rate for Gemini 4 Argon at low effort, 31.9%, cannot be a mean of binary outcomes over the stated 15 tasks times 5 attempts: no integer numerator over 75 falls in its rounding window [23.8875, 23.9625], while all 23 other printed construct rates do. Its printed 95% interval [10.7, 52.0] is also byte-identical to the same system's top-effort interval. The two signals together indicate a transcription fault in the paper rather than a measured value, and the paper prints nothing that resolves it: the lane's aggregate is 15.8 under either 31.9 or 32.0, and Table G2's per-task solves are top-effort only. The printed value is kept as published and this entry withholds it from automatic comparison; the lane's other results are not covered.BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table D2, row 'Gemini 4 Argon' tier 'low' effort 'low', column 'Construct design % [95% CI]'
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' Configuration: Gemini 4 Argon in Gemini CLI 0.63.0, high reasoning effort Task: BenchBench-Cloning construct design: Insulin intermediate construct 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 Evidence concern: excluded from comparisons Table D2's construct-design rate for Gemini 4 Argon at low effort, 31.9%, cannot be a mean of binary outcomes over the stated 15 tasks times 5 attempts: no integer numerator over 75 falls in its rounding window [23.8875, 23.9625], while all 23 other printed construct rates do. Its printed 95% interval [10.7, 52.0] is also byte-identical to the same system's top-effort interval. The two signals together indicate a transcription fault in the paper rather than a measured value, and the paper prints nothing that resolves it: the lane's aggregate is 15.8 under either 31.9 or 32.0, and Table G2's per-task solves are top-effort only. The printed value is kept as published and this entry withholds it from automatic comparison; the lane's other results are not covered.BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table D2, row 'Gemini 4 Argon' tier 'low' effort 'low', column 'Construct design % [95% CI]'
Methods, coverage and source Gemini 4 Argon 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 4 Argon' Configuration: GPT-6.1 Sol in Codex CLI 0.156.1, max reasoning effort Task: BenchBench-Cloning construct design: Insulin intermediate construct Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10) 4/5 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 Evidence concern: excluded from comparisons Table D2's construct-design rate for Gemini 4 Argon at low effort, 31.9%, cannot be a mean of binary outcomes over the stated 15 tasks times 5 attempts: no integer numerator over 75 falls in its rounding window [23.8875, 23.9625], while all 23 other printed construct rates do. Its printed 95% interval [10.7, 52.0] is also byte-identical to the same system's top-effort interval. The two signals together indicate a transcription fault in the paper rather than a measured value, and the paper prints nothing that resolves it: the lane's aggregate is 15.8 under either 31.9 or 32.0, and Table G2's per-task solves are top-effort only. The printed value is kept as published and this entry withholds it from automatic comparison; the lane's other results are not covered.BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table D2, row 'Gemini 4 Argon' tier 'low' effort 'low', column 'Construct design % [95% CI]'
Methods, coverage and source GPT-6.1 Sol 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 'GPT-6.1 Sol' Configuration: GPT-6 Astra in Codex CLI 0.156.1, max reasoning effort Task: 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 Evidence concern: excluded from comparisons Table D2's construct-design rate for Gemini 4 Argon at low effort, 31.9%, cannot be a mean of binary outcomes over the stated 15 tasks times 5 attempts: no integer numerator over 75 falls in its rounding window [23.8875, 23.9625], while all 23 other printed construct rates do. Its printed 95% interval [10.7, 52.0] is also byte-identical to the same system's top-effort interval. The two signals together indicate a transcription fault in the paper rather than a measured value, and the paper prints nothing that resolves it: the lane's aggregate is 15.8 under either 31.9 or 32.0, and Table G2's per-task solves are top-effort only. The printed value is kept as published and this entry withholds it from automatic comparison; the lane's other results are not covered.BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table D2, row 'Gemini 4 Argon' tier 'low' effort 'low', column 'Construct design % [95% CI]'
Methods, coverage and source GPT-6 Astra 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 'GPT-6 Astra' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: BenchBench-Cloning construct design: Insulin intermediate construct Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10) 4/5 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 Evidence concern: excluded from comparisons Table D2's construct-design rate for Gemini 4 Argon at low effort, 31.9%, cannot be a mean of binary outcomes over the stated 15 tasks times 5 attempts: no integer numerator over 75 falls in its rounding window [23.8875, 23.9625], while all 23 other printed construct rates do. Its printed 95% interval [10.7, 52.0] is also byte-identical to the same system's top-effort interval. The two signals together indicate a transcription fault in the paper rather than a measured value, and the paper prints nothing that resolves it: the lane's aggregate is 15.8 under either 31.9 or 32.0, and Table G2's per-task solves are top-effort only. The printed value is kept as published and this entry withholds it from automatic comparison; the lane's other results are not covered.BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table D2, row 'Gemini 4 Argon' tier 'low' effort 'low', column 'Construct design % [95% CI]'
Methods, coverage and source Grok 4.7 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 'Grok 4.7' Configuration: Kimi K3 in Pi 1.0.3, high reasoning effort Task: BenchBench-Cloning construct design: Insulin intermediate construct Dataset subset: BenchBench-Cloning construct-design tasks with a rubric model judge (10) 2/5 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 Evidence concern: excluded from comparisons Table D2's construct-design rate for Gemini 4 Argon at low effort, 31.9%, cannot be a mean of binary outcomes over the stated 15 tasks times 5 attempts: no integer numerator over 75 falls in its rounding window [23.8875, 23.9625], while all 23 other printed construct rates do. Its printed 95% interval [10.7, 52.0] is also byte-identical to the same system's top-effort interval. The two signals together indicate a transcription fault in the paper rather than a measured value, and the paper prints nothing that resolves it: the lane's aggregate is 15.8 under either 31.9 or 32.0, and Table G2's per-task solves are top-effort only. The printed value is kept as published and this entry withholds it from automatic comparison; the lane's other results are not covered.BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table D2, row 'Gemini 4 Argon' tier 'low' effort 'low', column 'Construct design % [95% CI]'
Methods, coverage and source Kimi K3 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 'Kimi K3'