All evidence cases
Terminal-Bench 2.1terminalC

Implement compact GPT-2 inference in C

Write a dependency-free C program under 5,000 bytes that loads GPT-2 TensorFlow checkpoints and BPE vocabulary and emits 20 argmax tokens.

gpt2-codegolf

Normalized profile

What this task asks for

Write a dependency-free C program under 5,000 bytes that loads GPT-2 TensorFlow checkpoints and BPE vocabulary and emits 20 argmax tokens. Remain under 5,000 source bytes. Compile with gcc -O3 -lm without dependencies. Read the checkpoint, BPE file, and prompt from command-line arguments. Continue output for exactly 20 argmax-selected tokens.

  • feature implementation
  • performance optimization
  • model inference
  • checkpoint loader
  • tokenizer
  • GPT-2
  • TensorFlow checkpoints
  • BPE
  • GCC
  • /app/gpt2.c
  • strict behavioral compatibility or exact-output validation
  • quantitative performance, accuracy, or resource constraints
  • native compilation and dependency 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-22.0.0highMixed2 errors3/5
claude-opus-4-7anthropic · 2026-05-01claude-code2.1.123maxNo passes5 errors0/5
claude-opus-4-7anthropic · 2026-05-01terminus-22.0.0maxNo passes5 errors0/5
claude-opus-4-8anthropic · 2026-07-09claude-code2.1.205highMixed4 errors1/5
claude-sonnet-5anthropic · 2026-07-09claude-code2.1.205highNo passes5 errors0/5
gemini-3-pro-previewgemini · 2026-05-01gemini-cli0.40.0highMixed3 errors1/5
gemini-3-pro-previewgemini · 2026-05-01terminus-22.0.0highNo passes5 errors0/5
gemini-3.1-pro-previewgemini · 2026-05-05gemini-cli0.40.0highMixed2 errors1/5
gemini-3.1-pro-previewgemini · 2026-05-05terminus-22.0.0highNo passes4 errors0/5
glm-5.1zai · 2026-05-01claude-code2.1.123maxNo passes5 errors0/5
gpt-5.5openai · 2026-05-01codex0.125.0xhighAll passed5/5
gpt-5.5openai · 2026-05-01terminus-22.0.0xhighNo passes5 errors0/5
gpt-5.6-lunaopenai · 2026-07-10codex0.144.0maxNo passes5 disqualified0/5
gpt-5.6-lunaopenai · 2026-07-11codex0.144.1maxMixed4 errors1/5
gpt-5.6-solopenai · 2026-07-10codex0.144.0maxMixed3 disqualified2/5
gpt-5.6-terraopenai · 2026-07-10codex0.144.0maxMixed3 disqualified2/5
gpt-5.6-terraopenai · 2026-07-11codex0.144.1maxMixed1 errors4/5
grok-4.5cursor · 2026-07-09cursor-cli2026.07.08-0c04a8adefaultNo passes5 disqualified0/5
muse-spark-1.1openai · 2026-07-09mini-swe-agent2.4.5xhighNo passes5 errors0/5