All evidence cases
Terminal-Bench 2.1terminalRedcode

Write a Core War warrior with target win rates

Create a Redcode warrior that meets separate 100-round win-rate thresholds against five supplied pMARS opponents without modifying them.

winning-avg-corewars

Normalized profile

What this task asks for

Create a Redcode warrior that meets separate 100-round win-rate thresholds against five supplied pMARS opponents without modifying them. Use core size 8000 and maximum 80,000 cycles. Win at least 75 of 100 rounds against stone, vampire, and paper. Win at least 33 of 100 rounds against snake and g2-clear. Leave every opponent file unchanged.

  • feature implementation
  • configuration tuning
  • test and validation
  • game program
  • battle simulator
  • pMARS
  • Core War
  • Redcode
  • my_warrior.red
  • 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-code2.1.167xhighNo passes5 errors0/5
claude-fable-5anthropic · 2026-06-05terminus-22.0.0highMixed2 errors3/5
claude-opus-4-7anthropic · 2026-05-01claude-code2.1.123maxMixed1 errors4/5
claude-opus-4-7anthropic · 2026-05-01terminus-22.0.0maxNo passes5 errors0/5
claude-opus-4-8anthropic · 2026-07-09claude-code2.1.205highMixed1 errors4/5
claude-sonnet-5anthropic · 2026-07-09claude-code2.1.205highMixed2 errors2/5
gemini-3-pro-previewgemini · 2026-05-01gemini-cli0.40.0highMixed1 errors2/5
gemini-3-pro-previewgemini · 2026-05-01terminus-22.0.0highMixed4/5
gemini-3.1-pro-previewgemini · 2026-05-05gemini-cli0.40.0highMixed4/5
gemini-3.1-pro-previewgemini · 2026-05-05terminus-22.0.0highMixed3/5
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-22.0.0xhighMixed1 disqualified4/5
gpt-5.6-lunaopenai · 2026-07-10codex0.144.0maxMixed1 errors · 2 disqualified2/5
gpt-5.6-lunaopenai · 2026-07-11codex0.144.1maxMixed3/5
gpt-5.6-solopenai · 2026-07-10codex0.144.0maxAll passed5/5
gpt-5.6-terraopenai · 2026-07-10codex0.144.0maxMixed2 disqualified3/5
gpt-5.6-terraopenai · 2026-07-11codex0.144.1maxAll passed5/5
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