All evidence cases
Terminal-Bench 2.1terminalCPythonJSON

Run MNIST PyTorch inference from a C CLI

Convert the supplied PyTorch model weights to JSON and implement a command-line executable that predicts one MNIST digit from an image.

pytorch-model-cli

Normalized profile

What this task asks for

Convert the supplied PyTorch model weights to JSON and implement a command-line executable that predicts one MNIST digit from an image. Invoke as ./cli_tool weights.json image.png. Load model parameters from weights.json. Print only one digit from 0 through 9. Store only the predicted digit in prediction.txt.

  • data transformation
  • feature implementation
  • model weights
  • inference runtime
  • command-line interface
  • PyTorch
  • MNIST
  • JSON
  • PNG
  • /app/cli_tool
  • /app/weights.json
  • /app/prediction.txt
  • reverse engineering from incomplete or indirect evidence
  • 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-code2.1.167xhighMixed4/5
claude-fable-5anthropic · 2026-06-05terminus-22.0.0highMixed4/5
claude-opus-4-7anthropic · 2026-05-01claude-code2.1.123maxMixed3/5
claude-opus-4-7anthropic · 2026-05-01terminus-22.0.0maxMixed4/5
claude-opus-4-8anthropic · 2026-07-09claude-code2.1.205highMixed1/5
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-22.0.0highMixed4/5
gemini-3.1-pro-previewgemini · 2026-05-05gemini-cli0.40.0highAll passed5/5
gemini-3.1-pro-previewgemini · 2026-05-05terminus-22.0.0highMixed3/5
glm-5.1zai · 2026-05-01claude-code2.1.123maxMixed4/5
gpt-5.5openai · 2026-05-01codex0.125.0xhighAll passed5/5
gpt-5.5openai · 2026-05-01terminus-22.0.0xhighAll passed5/5
gpt-5.6-lunaopenai · 2026-07-10codex0.144.0maxAll passed5/5
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 · 2026-07-11codex0.144.1maxMixed4/5
grok-4.5cursor · 2026-07-09cursor-cli2026.07.08-0c04a8adefaultAll passed5/5
muse-spark-1.1openai · 2026-07-09mini-swe-agent2.4.5xhighAll passed5/5