Back to results

CompBioBench item

gene-expression-query-q1

Question

Retrieve the median expression level for APOE from the 'Brain_Cortex' samples in the GTEx v8 reference dataset. The value should be in Transcripts Per Million as an integer.

Predicted answer
604Most likely answer for this question; not uniquely determined from submitted scores.
Domain
Transcriptomics
Question style
Retrieval

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

Matches predictionUDT-only
Answer604
Workflow
GTEx APOE Brain Cortex median TPMGTEx v8 median TPM header probeGTEx APOE Brain Cortex median TPM exact column
Total tokens
635.8K
Output
5.6K
Codex GPT-5.5

Replicate 2

Matches predictionStandard tools only
Answer604
Workflow
Tp Head ToolTp Grep ToolSelect columns
Total tokens
675.0K
Output
4.9K
Codex GPT-5.5

Replicate 3

Matches predictionStandard tools only
Answer604
Workflow
Galaxy dataset inspection
Total tokens
744.2K
Output
6.6K

Codex GPT-5.6 Sol

3 replicates
Codex GPT-5.6 Sol

Replicate 1

Matches predictionStandard tools only
Answer604
Workflow
Upload1Tp Grep ToolSelect columns
Total tokens
6.3M
Output
10.9K
Codex GPT-5.6 Sol

Replicate 2

Matches predictionStandard tools only
Answer604
Workflow
Converter Gz To UncompressedGrepSelect columns
Total tokens
1.3M
Output
6.9K
Codex GPT-5.6 Sol

Replicate 3

Matches predictionStandard tools only
Answer604
Workflow
Upload1Converter Gz To UncompressedShow Beginning1Filter TabularFilter rows3 more tools
Total tokens
2.6M
Output
9.5K

Codex + DeepSeek-v4-pro-0813

3 replicates
Codex + DeepSeek-v4-pro-0813

Replicate 1

Matches predictionStandard tools only
Answer604
Workflow
GrepSelect columnsTable ComputeAdd A Column1
Total tokens
2.0M
Output
20.4K
Codex + DeepSeek-v4-pro-0813

Replicate 2

Matches predictionStandard tools only
Answer604
Workflow
Filter Tabular
Total tokens
748.6K
Output
7.8K
Codex + DeepSeek-v4-pro-0813

Replicate 3

Matches predictionStandard tools only
Answer604
Workflow
Filter TabularDatamash Ops
Total tokens
3.5M
Output
19.8K

Codex GPT-5.6 Luna

3 replicates
Codex GPT-5.6 Luna

Replicate 1

Matches predictionStandard tools only
Answer604
Workflow
Filter TabularTp Grep ToolSelect columnsDatamash TransposeDatamash Ops1 more tools
Total tokens
7.6M
Output
22.7K
Codex GPT-5.6 Luna

Replicate 2

Matches predictionUDT-only
Answer604
Workflow
GTEx APOE Brain Cortex Median Validation
Total tokens
2.3M
Output
14.6K
Codex GPT-5.6 Luna

Replicate 3

Matches predictionStandard tools only
Answer604
Workflow
Filter TabularDatamash Transpose
Total tokens
9.9M
Output
31.4K

Anycode

13/13 terminal item results

Codex GPT-5.5

3 replicates
Codex GPT-5.5

Replicate 1

Matches prediction
Answer604
Workflow
Local code
Codex GPT-5.5

Replicate 2

Matches prediction
Answer604
Workflow
Local code
Codex GPT-5.5

Replicate 3

Matches prediction
Answer604
Workflow
Local code

Codex GPT-5.6 Sol

3 replicates
Codex GPT-5.6 Sol

Replicate 1

Matches prediction
Answer604
Workflow
Local code
Codex GPT-5.6 Sol

Replicate 2

Matches prediction
Answer604
Workflow
Local code
Codex GPT-5.6 Sol

Replicate 3

Matches prediction
Answer604
Workflow
Local code

Codex + DeepSeek-v4-pro-0813

3 replicates
Codex + DeepSeek-v4-pro-0813

Replicate 1

Matches prediction
Answer604
Workflow
Local code
Total tokens
136.6K
Output
2.4K
Codex + DeepSeek-v4-pro-0813

Replicate 2

Matches prediction
Answer604
Workflow
Local codePython
Total tokens
287.0K
Output
2.9K
Codex + DeepSeek-v4-pro-0813

Replicate 3

Matches prediction
Answer604
Workflow
Local codePython
Total tokens
240.8K
Output
3.6K

Codex GPT-5.6 Luna

3 replicates
Codex GPT-5.6 Luna

Replicate 1

Matches prediction
Answer604
Workflow
Local code
Codex GPT-5.6 Luna

Replicate 2

Matches prediction
Answer604
Workflow
Local code
Codex GPT-5.6 Luna

Replicate 3

Matches prediction
Answer604
Workflow
Local code

Codex GPT-6 Astra

1 replicate
Codex GPT-6 Astra

Replicate 1

Matches prediction
Answer604
Workflow
Local code
Total tokens
45.2K
Output
320