All evidence cases
Terminal-Bench 2.1terminalFastText binary format

Train a compact Yelp FastText classifier

Train a FastText text classifier on the supplied Yelp reviews that exceeds 0.62 held-out accuracy while keeping the model under 150MB.

train-fasttext

Normalized profile

What this task asks for

Train a FastText text classifier on the supplied Yelp reviews that exceeds 0.62 held-out accuracy while keeping the model under 150MB. Train on the data directory's Yelp examples. Achieve at least 0.62 accuracy on same-distribution private data. Keep model.bin below 150MB.

  • model training
  • configuration tuning
  • test and validation
  • training dataset
  • text classifier
  • FastText
  • Yelp reviews
  • /app/model.bin
  • quantitative performance, accuracy, or resource constraints

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-code2.1.167xhighMixed1 errors2/5
claude-fable-5anthropic · 2026-06-05terminus-22.0.0highMixed3 errors1/5
claude-opus-4-7anthropic · 2026-05-01claude-code2.1.123maxNo passes3 errors0/5
claude-opus-4-7anthropic · 2026-05-01terminus-22.0.0maxNo passes4 errors0/5
claude-opus-4-8anthropic · 2026-07-09claude-code2.1.205highNo passes2 errors0/5
claude-sonnet-5anthropic · 2026-07-09claude-code2.1.205highMixed4 errors1/5
gemini-3-pro-previewgemini · 2026-05-01gemini-cli0.40.0highMixed1 errors2/5
gemini-3-pro-previewgemini · 2026-05-01terminus-22.0.0highMixed1/5
gemini-3.1-pro-previewgemini · 2026-05-05gemini-cli0.40.0highNo passes3 errors0/5
gemini-3.1-pro-previewgemini · 2026-05-05terminus-22.0.0highNo passes0/5
glm-5.1zai · 2026-05-01claude-code2.1.123maxNo passes5 errors0/5
gpt-5.5openai · 2026-05-01codex0.125.0xhighNo passes4 errors0/5
gpt-5.5openai · 2026-05-01terminus-22.0.0xhighNo passes4 errors0/5
gpt-5.6-lunaopenai · 2026-07-10codex0.144.0maxNo passes4 errors0/5
gpt-5.6-lunaopenai · 2026-07-11codex0.144.1maxNo passes3 errors0/5
gpt-5.6-solopenai · 2026-07-10codex0.144.0maxAll passed5/5
gpt-5.6-terraopenai · 2026-07-10codex0.144.0maxMixed4 errors1/5
gpt-5.6-terraopenai · 2026-07-11codex0.144.1maxNo passes4 errors0/5
grok-4.5cursor · 2026-07-09cursor-cli2026.07.08-0c04a8adefaultMixed2 errors2/5
muse-spark-1.1openai · 2026-07-09mini-swe-agent2.4.5xhighNo passes2 errors0/5