All evidence cases
Terminal-Bench 2.1terminalPythonCSV

Refine cell boxes into MobileSAM contours

Implement a CPU MobileSAM pipeline that converts every rectangular or polygonal cell annotation into one nonoverlapping contiguous polyline and updates its geometry fields.

sam-cell-seg

Normalized profile

What this task asks for

Implement a CPU MobileSAM pipeline that converts every rectangular or polygonal cell annotation into one nonoverlapping contiguous polyline and updates its geometry fields. Accept weights, output, RGB, and CSV paths through argparse. Use MobileSAM rather than original SAM. Run without a GPU or source modifications. Refine every row to one contiguous nonrectangular polyline. Prevent overlap and update only geometry columns while preserving the CSV schema.

  • feature implementation
  • data transformation
  • segmentation pipeline
  • cell masks
  • command-line interface
  • MobileSAM
  • PyTorch
  • OpenCV
  • pandas
  • histopathology
  • /app/convert_masks.py
  • refined mask CSV
  • strict behavioral compatibility or exact-output validation
  • specialized algorithmic or domain reasoning
  • cross-language or cross-format integration
  • changes span multiple components or interfaces

Published evidence

Model × harness outcomes

Counts are tied to these exact configurations. Harnesses are not treated as equivalent across benchmarks.

Models
13
Configurations
20
Trials
100

Showing 20 of 20 configurations

ModelHarnessEffortResultPasses
claude-fable-5anthropic · 2026-06-07claude-code2.1.167xhighAll passed5/5
claude-fable-5anthropic · 2026-06-05terminus-22.0.0highAll passed5/5
claude-opus-4-7anthropic · 2026-05-01claude-code2.1.123maxMixed4/5
claude-opus-4-7anthropic · 2026-05-01terminus-22.0.0maxAll passed5/5
claude-opus-4-8anthropic · 2026-07-09claude-code2.1.205highMixed4/5
claude-sonnet-5anthropic · 2026-07-09claude-code2.1.205highMixed4/5
gemini-3-pro-previewgemini · 2026-05-01gemini-cli0.40.0highAll passed5/5
gemini-3-pro-previewgemini · 2026-05-01terminus-22.0.0highAll passed5/5
gemini-3.1-pro-previewgemini · 2026-05-05gemini-cli0.40.0highMixed4/5
gemini-3.1-pro-previewgemini · 2026-05-05terminus-22.0.0highAll passed5/5
glm-5.1zai · 2026-05-01claude-code2.1.123maxMixed2/5
gpt-5.5openai · 2026-05-01codex0.125.0xhighMixed4/5
gpt-5.5openai · 2026-05-01terminus-22.0.0xhighMixed4/5
gpt-5.6-lunaopenai · 2026-07-10codex0.144.0maxMixed4/5
gpt-5.6-lunaopenai · 2026-07-11codex0.144.1maxAll passed5/5
gpt-5.6-solopenai · 2026-07-10codex0.144.0maxAll passed5/5
gpt-5.6-terraopenai · 2026-07-10codex0.144.0maxMixed4/5
gpt-5.6-terraopenai · 2026-07-11codex0.144.1maxAll passed5/5
grok-4.5cursor · 2026-07-09cursor-cli2026.07.08-0c04a8adefaultMixed4/5
muse-spark-1.1openai · 2026-07-09mini-swe-agent2.4.5xhighAll passed5/5