Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Benchmark: BenchBench-Cloning protocol-development set Dataset subset: BenchBench-Cloning protocol-development tasks (50) 34% Success rate (protocol-development pass@10: probability that at least one of 10 attempts passes; best-of-k, never comparable with single-attempt pass rate; top reasoning tier, the highest of this system's three settings)percent · higher
Uncertainty: 95% CI 22.0 to 48.0. 95% confidence intervals from 20,000 bootstrap resamples of the tasks, retaining all attempts of each sampled task (Section 3.4).
Coverage: Not reported scored / Not reported eligible
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 protocol development, pass@10
benchbench-cloning-20261106-protocol-protocol-development-pass-at-10
Aggregation: Not reported
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G1, row 'Grok 4.7', column 'pass@10 % [95% CI]' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Benchmark: BenchBench-Cloning protocol-development set Dataset subset: BenchBench-Cloning protocol-development tasks (50) 22.9% Success rate (protocol-development pass@5: probability that at least one of 5 attempts passes; best-of-k, never comparable with single-attempt pass rate; top reasoning tier, the highest of this system's three settings)percent · higher
Uncertainty: 95% CI 13.8 to 32.6. 95% confidence intervals from 20,000 bootstrap resamples of the tasks, retaining all attempts of each sampled task (Section 3.4).
Coverage: Not reported scored / Not reported eligible
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 protocol development, pass@5
benchbench-cloning-20261106-protocol-protocol-development-pass-at-5
Aggregation: Not reported
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G1, row 'Grok 4.7', column 'pass@5 % [95% CI]' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Benchmark: BenchBench-Cloning protocol-development set Dataset subset: BenchBench-Cloning protocol-development tasks (50) 0 Count (protocol-development tasks solved in every one of ten attempts, out of 50; a coverage count under repeated sampling, not a single-attempt performance measure; top reasoning tier, the highest of this system's three settings)count · higher
Uncertainty: Not reported by the source: Table G1 prints no interval for the solved-task counts.
Coverage: 50/50 tasks 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 protocol development, tasks solved in every one of ten attempts
benchbench-cloning-20261106-protocol-protocol-development-tasks-solved-every-attempt
Aggregation: Not reported
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G1, row 'Grok 4.7', column 'Solved all' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Benchmark: BenchBench-Cloning protocol-development set Dataset subset: BenchBench-Cloning protocol-development tasks (50) 17 Count (protocol-development tasks solved at least once in ten attempts, out of 50; a coverage count under repeated sampling, not a single-attempt performance measure; top reasoning tier, the highest of this system's three settings)count · higher
Uncertainty: Not reported by the source: Table G1 prints no interval for the solved-task counts.
Coverage: 50/50 tasks 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 protocol development, tasks solved at least once in ten attempts
benchbench-cloning-20261106-protocol-protocol-development-tasks-solved-once
Aggregation: Not reported
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G1, row 'Grok 4.7', column 'Solved >=1' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: 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 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: 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 'Grok 4.7' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: 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 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: 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 'Grok 4.7' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: 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 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: 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 'Grok 4.7' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: BenchBench-Cloning construct design: Dual-luciferase frame panel Dataset subset: BenchBench-Cloning construct-design tasks graded deterministically only (5) 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 only, no model 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: Dual-luciferase frame panel
benchbench-cloning-20261106-protocol-construct-design-per-task-deterministic
Aggregation: Not reported
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Dual-luciferase frame panel', column 'Grok 4.7' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: 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 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: 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 'Grok 4.7' 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: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: BenchBench-Cloning construct design: Insulin two-chain constructs 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 Grok 4.7 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 'Grok 4.7' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: BenchBench-Cloning construct design: Matched promoter panel Dataset subset: BenchBench-Cloning construct-design tasks graded deterministically only (5) 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 only, no model 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: Matched promoter panel
benchbench-cloning-20261106-protocol-construct-design-per-task-deterministic
Aggregation: Not reported
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Matched promoter panel', column 'Grok 4.7' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: BenchBench-Cloning construct design: Minimal-edit recoding 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 Grok 4.7 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 'Grok 4.7' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: BenchBench-Cloning construct design: MPRA construct rebuild Dataset subset: BenchBench-Cloning construct-design tasks graded deterministically only (5) 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 only, no model 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: MPRA construct rebuild
benchbench-cloning-20261106-protocol-construct-design-per-task-deterministic
Aggregation: Not reported
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'MPRA construct rebuild', column 'Grok 4.7' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: 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 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: 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 'Grok 4.7' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: BenchBench-Cloning construct design: Reporter choice from data Dataset subset: BenchBench-Cloning construct-design tasks graded deterministically only (5) 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 only, no model 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: Reporter choice from data
benchbench-cloning-20261106-protocol-construct-design-per-task-deterministic
Aggregation: Not reported
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Reporter choice from data', column 'Grok 4.7' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: BenchBench-Cloning construct design: Sodium-channel promoter repair Dataset subset: BenchBench-Cloning construct-design tasks graded deterministically only (5) 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 only, no model 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: Sodium-channel promoter repair
benchbench-cloning-20261106-protocol-construct-design-per-task-deterministic
Aggregation: Not reported
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table G2, row 'Sodium-channel promoter repair', column 'Grok 4.7' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: 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 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: 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 'Grok 4.7' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Task: 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 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: 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 'Grok 4.7' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Benchmark: BenchBench-Cloning Dataset subset: BenchBench-Cloning protocol-development tasks (50) 10.9% Success rate (aggregate single-attempt score over all 65 tasks, task-weighted 50/65 protocol development and 15/65 construct design; top reasoning tier, the highest of this system's three settings)percent · higher
Uncertainty: 95% CI 6.3 to 16.2. 95% confidence intervals from 20,000 bootstrap resamples of the tasks, retaining all attempts of each sampled task (Section 3.4).
Coverage: 575/575 attempts scored (500 protocol-development attempts plus 75 construct-design attempts; the weights are over tasks, 50/65 and 15/65.)
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 at xhigh effort on BenchBench-Cloning aggregate score
benchbench-cloning-20261106-protocol-aggregate-score
Aggregation: Not reported
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table D2, row 'Grok 4.7' tier 'top' effort 'xhigh', column 'Aggregate % [95% CI]'; the same cell is printed in Table 2, row 'Grok 4.7', column 'Aggregate %' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Benchmark: BenchBench-Cloning construct-design set Dataset subset: BenchBench-Cloning construct-design tasks (15) 26.7% Success rate (construct-design pass rate at a single attempt, pass at a final score of at least 0.9, deterministic grading on five tasks and deterministic multiplied by a GPT-6 Astra rubric score on ten; top reasoning tier, the highest of this system's three settings)percent · higher
Uncertainty: 95% CI 9.3 to 46.7. 95% confidence intervals from 20,000 bootstrap resamples of the tasks, retaining all attempts of each sampled task (Section 3.4).
Coverage: 75/75 attempts scored (15 tasks x 5 attempts. The Table G2 per-task solve counts for this system sum to 20, and 20/75 reproduces the printed rate.)
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 at xhigh effort on BenchBench-Cloning construct-design pass rate
benchbench-cloning-20261106-protocol-construct-design-pass-rate
Aggregation: Not reported
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table D2, row 'Grok 4.7' tier 'top' effort 'xhigh', column 'Construct design % [95% CI]'; the same cell is printed in Table 2, row 'Grok 4.7', column 'Construct design %' Configuration: Grok 4.7 in Grok Build 1.0.46, xhigh reasoning effort Benchmark: BenchBench-Cloning protocol-development set Dataset subset: BenchBench-Cloning protocol-development tasks (50) 6.2% Success rate (protocol-development pass rate at a single attempt (pass@1), simulator-graded and binary per attempt; top reasoning tier, the highest of this system's three settings)percent · higher
Uncertainty: 95% CI 3.4 to 9.2. 95% confidence intervals from 20,000 bootstrap resamples of the tasks, retaining all attempts of each sampled task (Section 3.4).
Coverage: 498/500 attempts scored (Table E1 prints 498 graded attempts and 31 passed; Table E2 prints 548 recorded and 50 unscored. Appendix B's budget is 500 attempts. The printed rate does not say which denominator was used: 31/500 and 31/498 = 6.225 both round to the printed value.)
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 at xhigh effort on BenchBench-Cloning protocol-development pass rate
benchbench-cloning-20261106-protocol-protocol-development-pass-rate
Aggregation: Not reported
BenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development (arXiv:2610.33355v1) · Table D2, row 'Grok 4.7' tier 'top' effort 'xhigh', column 'Protocol dev. % [95% CI]'; the same cell is printed in Table 2, row 'Grok 4.7', column 'Protocol dev. %'