Back to results

CompBioBench item

gtf-5-utr-median-len-q1

Question

From the given GTF MANE.GRCh38.v1.3.refseq_genomic.gtf.gz, report the median 5' UTR, CDS, and 3' UTR lengths (use numpy median function, rounded down to nearest integer). Only consider MANE Select transcripts and those on standard chromosomes. Consider stop codon as part of CDS. Return a semicolon separated string with no space, e.g. "45;551;23".

Inferred answer
133;1296;1050Uniquely inferred from submitted scores.
Domain
Transcriptomics
Question style
Routine Analysis

An answer can be uniquely inferred for 54 of 100 questions from submitted scores. Green: correct · Red: incorrect. For questions without a uniquely determined answer: Blue: matches prediction · Orange: differs from prediction. These are inferred answer checks, not official per-question grades.

Galaxy

12/12 terminal item results

UDT = user-defined tool: custom code executed by Galaxy. Route badges summarize analysis tools, excluding uploads and automatic conversions. How usage is counted.

Codex GPT-5.5

3 replicates
Codex GPT-5.5

Replicate 1

CorrectUDT-only
Answer133;1296;1050
Workflow
MANE UTR CDS lengthsMANE UTR CDS lengths v2MANE UTR CDS lengths v3MANE UTR CDS lengths v4
Codex GPT-5.5

Replicate 2

CorrectUDT + standard tools
Answer133;1296;1050
Workflow
MANE GTF DiagnosticMANE GTF Diagnostic v2UDT Echo Probe MANEUDT Echo Probe MANE 2UDT Echo Probe MANE 310 more tools
Total tokens
7.9M
Output
28.8K
Codex GPT-5.5

Replicate 3

RerunCorrectUDT-only
Answer133;1296;1050
Workflow
MANE GTF diagnosticMANE length medians
Total tokens
398.3K
Output
7.1K

Codex GPT-5.6 Sol

3 replicates
Codex GPT-5.6 Sol

Replicate 1

CorrectUDT-only
Answer133;1296;1050
Workflow
Summarize MANE GTF UTR and CDS lengthsCalculate MANE GTF UTR and CDS mediansCalculate MANE GTF UTR and CDS medians with NumPyValidated MANE GTF UTR and CDS mediansFinal validated MANE GTF UTR and CDS medians
Total tokens
2.3M
Output
12.2K
Codex GPT-5.6 Sol

Replicate 2

CorrectUDT-only
Answer133;1296;1050
Workflow
MANE GTF diagnosticMANE Select standard chromosome UTR CDS medians
Total tokens
716.7K
Output
8.6K
Codex GPT-5.6 Sol

Replicate 3

CorrectUDT + standard tools
Answer133;1296;1050
Workflow
MANE v1.3 transcript structure diagnosticsTp Head ToolGrepGtftobed12MANE v1.3 BED12 UTR and CDS medians7 more tools
Total tokens
21.5M
Output
34.7K

Codex + DeepSeek-v4-pro-0813

3 replicates
Codex + DeepSeek-v4-pro-0813

Replicate 1

CorrectUDT-only
Answer133;1296;1050
Workflow
MANE UTR MedianMANE UTR Median v2
Total tokens
1.2M
Output
17.9K
Codex + DeepSeek-v4-pro-0813

Replicate 2

CorrectUDT + standard tools
Answer133;1296;1050
Workflow
MANE UTR mediansMANE UTR medians v2MANE UTR medians v3Datamash Ops
Total tokens
1.8M
Output
23.1K
Codex + DeepSeek-v4-pro-0813

Replicate 3

RerunCorrectUDT + standard tools
Answer133;1296;1050
Workflow
Filter annotationConvert transcripts to BED12Feature-length calculationMedian summary
Total tokens
15.8M
Output
69.7K

Codex GPT-5.6 Luna

3 replicates
Codex GPT-5.6 Luna

Replicate 1

CorrectUDT + standard tools
Answer133;1296;1050
Workflow
MANE GTF inspectionCat Multi DatasetsUDT routing probeMANE GTF inspection refinedMANE length diagnostics1 more tools
Total tokens
13.3M
Output
47.9K
Codex GPT-5.6 Luna

Replicate 2

CorrectUDT + standard tools
Answer133;1296;1050
Workflow
MANE GTF DiagnosticMANE UDT Render ProbeMANE UDT Minimal ProbeMANE UDT Documentation ProbeTp Head Tool12 more tools
Total tokens
25.0M
Output
78.6K
Codex GPT-5.6 Luna

Replicate 3

CorrectUDT + standard tools
Answer133;1296;1050
Workflow
MANE GTF ProbeMANE GTF Probe v2MANE Command ProbeGff Filter By AttributeConverter Gz To Uncompressed8 more tools
Total tokens
36.2M
Output
94.2K

Anycode

13/13 terminal item results

Codex GPT-5.5

3 replicates
Codex GPT-5.5

Replicate 1

Correct
Answer133;1296;1050
Workflow
Local codePython
Codex GPT-5.5

Replicate 2

Correct
Answer133;1296;1050
Workflow
Local codePython
Codex GPT-5.5

Replicate 3

Correct
Answer133;1296;1050
Workflow
Local codePython

Codex GPT-5.6 Sol

3 replicates
Codex GPT-5.6 Sol

Replicate 1

Correct
Answer133;1296;1050
Workflow
Local codePython
Codex GPT-5.6 Sol

Replicate 2

Correct
Answer133;1296;1050
Workflow
Local codePython
Codex GPT-5.6 Sol

Replicate 3

Correct
Answer133;1296;1050
Workflow
Local codePython

Codex + DeepSeek-v4-pro-0813

3 replicates
Codex + DeepSeek-v4-pro-0813

Replicate 1

Correct
Answer133;1296;1050
Workflow
Local codePython
Total tokens
305.7K
Output
11.4K
Codex + DeepSeek-v4-pro-0813

Replicate 2

Correct
Answer133;1296;1050
Workflow
Local codePython
Total tokens
383.2K
Output
13.8K
Codex + DeepSeek-v4-pro-0813

Replicate 3

Correct
Answer133;1296;1050
Workflow
Local codePython
Total tokens
389.0K
Output
15.1K

Codex GPT-5.6 Luna

3 replicates
Codex GPT-5.6 Luna

Replicate 1

Correct
Answer133;1296;1050
Workflow
Local codePython
Codex GPT-5.6 Luna

Replicate 2

Correct
Answer133;1296;1050
Workflow
Local codePython
Codex GPT-5.6 Luna

Replicate 3

Correct
Answer133;1296;1050
Workflow
Local codePython

Codex GPT-6 Astra

1 replicate
Codex GPT-6 Astra

Replicate 1

Correct
Answer133;1296;1050
Workflow
Local codePython
Total tokens
60.4K
Output
1.2K