All evidence cases
Terminal-Bench 2.1terminalC

Recreate a compiled path tracer in C

Reverse-engineer the mystery executable into compact standalone C source whose isolated behavior and generated output are identical.

path-tracing-reverse

Normalized profile

What this task asks for

Reverse-engineer the mystery executable into compact standalone C source whose isolated behavior and generated output are identical. Match the operation of /app/mystery exactly. Remain below 2KB when gzip-compressed. Do not invoke the original executable. Run independently after static compilation.

  • feature implementation
  • data transformation
  • test and validation
  • native executable
  • renderer
  • binary analysis
  • GCC
  • /app/mystery.c
  • reverse engineering from incomplete or indirect evidence
  • strict behavioral compatibility or exact-output validation
  • 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 errors4/5
claude-fable-5anthropic · 2026-06-05terminus-22.0.0highNo passes5 errors0/5
claude-opus-4-7anthropic · 2026-05-01claude-code2.1.123maxMixed4 errors1/5
claude-opus-4-7anthropic · 2026-05-01terminus-22.0.0maxNo passes5 errors0/5
claude-opus-4-8anthropic · 2026-07-09claude-code2.1.205highAll passed5/5
claude-sonnet-5anthropic · 2026-07-09claude-code2.1.205highAll passed5/5
gemini-3-pro-previewgemini · 2026-05-01gemini-cli0.40.0highMixed2 errors · 1 disqualified2/5
gemini-3-pro-previewgemini · 2026-05-01terminus-22.0.0highNo passes2 errors · 2 disqualified0/5
gemini-3.1-pro-previewgemini · 2026-05-05gemini-cli0.40.0highMixed2 errors1/5
gemini-3.1-pro-previewgemini · 2026-05-05terminus-22.0.0highMixed4 errors1/5
glm-5.1zai · 2026-05-01claude-code2.1.123maxNo passes4 errors0/5
gpt-5.5openai · 2026-05-01codex0.125.0xhighAll passed5/5
gpt-5.5openai · 2026-05-01terminus-22.0.0xhighMixed1 errors4/5
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 · 2026-07-10codex0.144.0maxMixed1 disqualified4/5
gpt-5.6-terraopenai · 2026-07-10codex0.144.0maxAll passed5/5
gpt-5.6-terraopenai · 2026-07-11codex0.144.1maxAll passed5/5
grok-4.5cursor · 2026-07-09cursor-cli2026.07.08-0c04a8adefaultMixed1 errors4/5
muse-spark-1.1openai · 2026-07-09mini-swe-agent2.4.5xhighMixed2 errors3/5