Frontier Log

Claude Fable 5.2 vs Claude Opus 5.5

Claude Fable 5.2Claude Opus 5.5
Released
Input / 1M tokens$8$4
Cached input / 1M tokens$0.20$0.20
Output / 1M tokens$40$20
Context window1M1M
Output limit128K128K
Benchmarks
Humanity's Last Exam No tools, full set (2,500 questions)73.2%164.4%
Humanity's Last Exam With tools, full set (2,500 questions)74.2%267.7%3
SWE-bench Pro Set not stated93.0%489.9%5
Terminal-Bench 4.067.6%666.4%7
Terminal-Bench Science 0.174.6%858.7%9
AutomationBench 1.0.6 Private set51.4%1040.0%11
OSWorld 2.1 Offline set (82 tasks), partial score89.3%1287.2%13
OSWorld 2.1 Offline set (82 tasks), strict pass rate54.6%1453.2%15
FrontierSWE v269.9%1662.3%17
DeepSWE v1.174.3%1874.2%19
Chartography No tools73.4%2064.4%21
Chartography With tools91.6%2289.0%23

Download image

Claude Fable 5.2Claude Opus 5.5
Other benchmarks
OSWorld 2.1 Full set (108 tasks), partial scoreNo data81.8%24
OSWorld 2.1 Full set (108 tasks), strict pass rateNo data48.7%25
OSWorld 2.0, release not stated Anthropic's Sep 10 files, partialNo data81.8%26
OSWorld 2.0, release not stated Anthropic's Sep 10 files, strictNo data48.7%27
FrontierCode 1.1 Main setNo data54.6%28
FrontierCode 1.1 Extended setNo data65.3%29
ARC-AGI-3 Semi-Private set (55 environments)79.26%30No data

Notes

  1. Humanity's Last Exam, No tools, full set (2,500 questions), Claude Fable 5.2: max effort · thinking set to auto · average of 5 trials · 980k-token task budget per attempt, no context compaction · Claude Opus 4.6 as model grader
  2. Humanity's Last Exam, With tools, full set (2,500 questions), Claude Fable 5.2: highest available effort, max effort, per the system card · thinking set to auto, per the system card · average of 5 trials, per the system card · web search, web fetch, programmatic tool calling and code execution, HLE sources blocklisted, per the system card · 980k-token task budget per attempt, no context compaction, per the system card · Claude Opus 4.6 as model grader, flagged transcripts reviewed by Claude Opus 5, confirmed cheating graded incorrect, per the system card · safeguards on
  3. Humanity's Last Exam, With tools, full set (2,500 questions), Claude Opus 5.5: max effort
  4. SWE-bench Pro, Set not stated, Claude Fable 5.2: max effort · adaptive thinking · average of 5 trials
  5. SWE-bench Pro, Set not stated, Claude Opus 5.5: max effort · adaptive thinking · average of 5 trials
  6. Terminal-Bench 4.0, Claude Fable 5.2: Claude Code in --bare mode · max effort · 10 trials per task · no internet access · safeguards on
  7. Terminal-Bench 4.0, Claude Opus 5.5: xhigh effort · standard error ±2.6 points
  8. Terminal-Bench Science 0.1, Claude Fable 5.2: Claude Code in --bare mode · highest available effort · averaged over 10 trials per task, per the system card · no internet access, per the system card · safeguards on, flagged requests answered by a fallback model (1.3% of requests), per the system card · standard error ±4.3 points, per the system card
  9. Terminal-Bench Science 0.1, Claude Opus 5.5: max effort · standard error ±3.5 to 5 points
  10. AutomationBench 1.0.6, Private set, Claude Fable 5.2: Run by Zapier · highest available effort · safeguards on · set and release 1.0.6 named in the system card, which prints the same figure
  11. AutomationBench 1.0.6, Private set, Claude Opus 5.5: Run by Zapier · without fallback models · set and release 1.0.6 named in the Claude Sonnet 5.5 system card, which prints the same figure
  12. OSWorld 2.1, Offline set (82 tasks), partial score, Claude Fable 5.2: highest available effort · safeguards on
  13. OSWorld 2.1, Offline set (82 tasks), partial score, Claude Opus 5.5: max effort · mean of 5 attempts
  14. OSWorld 2.1, Offline set (82 tasks), strict pass rate, Claude Fable 5.2: max effort · mean of 5 attempts
  15. OSWorld 2.1, Offline set (82 tasks), strict pass rate, Claude Opus 5.5: max effort · mean of 5 attempts
  16. FrontierSWE v2, Claude Fable 5.2: Run by Proximal · Proximal's agent harness · highest available effort · mean of 5 trials per task, per the system card · 20-hour budget · safeguards on
  17. FrontierSWE v2, Claude Opus 5.5: Run by Proximal · Proximal's agent harness · highest available effort · mean of 5 trials per task, per the system card · 20-hour budget · safeguards on
  18. DeepSWE v1.1, Claude Fable 5.2: average of 5 trials
  19. DeepSWE v1.1, Claude Opus 5.5: average of 5 trials
  20. Chartography, No tools, Claude Fable 5.2: highest available effort · safeguards on
  21. Chartography, No tools, Claude Opus 5.5: max effort · adaptive thinking · average of 5 runs · Gemini 3.5 Flash grader
  22. Chartography, With tools, Claude Fable 5.2: max effort · adaptive thinking · average of 5 runs · container and image-cropping tool · Gemini 3.5 Flash grader
  23. Chartography, With tools, Claude Opus 5.5: max effort · adaptive thinking
  24. OSWorld 2.1, Full set (108 tasks), partial score, Claude Opus 5.5: max effort · mean of 5 runs · September 10, 2026 task files · the system card labels it OSWorld 2.0
  25. OSWorld 2.1, Full set (108 tasks), strict pass rate, Claude Opus 5.5: max effort · mean of 5 runs · September 10, 2026 task files
  26. OSWorld 2.0, release not stated, Anthropic's Sep 10 files, partial, Claude Opus 5.5: max effort · mean of 5 runs
  27. OSWorld 2.0, release not stated, Anthropic's Sep 10 files, strict, Claude Opus 5.5: max effort · mean of 5 runs
  28. FrontierCode 1.1, Main set, Claude Opus 5.5: Run by Cognition · Claude Code harness · medium effort
  29. FrontierCode 1.1, Extended set, Claude Opus 5.5: Run by Cognition · Claude Code harness · medium effort
  30. ARC-AGI-3, Semi-Private set (55 environments), Claude Fable 5.2: Run by ARC Prize Foundation · Standard harness · high effort

Related

All comparisons