Frontier Log

Claude Fable 5.2 vs Claude Mythos 5.2

Claude Fable 5.2Claude Mythos 5.2
Released
Input / 1M tokens$8$8
Cached input / 1M tokens$0.20$0.20
Output / 1M tokens$40$40
Context window1M1M
Output limit128K128K
Benchmarks
Terminal-Bench 4.067.6%170.5%2
Terminal-Bench Science 0.174.6%375.3%4

Download image

Claude Fable 5.2Claude Mythos 5.2
Other benchmarks
Humanity's Last Exam No tools, full set (2,500 questions)73.2%5No data
Humanity's Last Exam With tools, full set (2,500 questions)74.2%6No data
SWE-bench Pro Set not stated93.0%7No data
AutomationBench 1.0.6 Private set51.4%8No data
OSWorld 2.1 Offline set (82 tasks), partial score89.3%9No data
OSWorld 2.1 Offline set (82 tasks), strict pass rate54.6%10No data
FrontierSWE v269.9%11No data
DeepSWE v1.174.3%12No data
ARC-AGI-3 Semi-Private set (55 environments)79.26%13No data
Chartography No tools73.4%14No data
Chartography With tools91.6%15No data

Notes

  1. Terminal-Bench 4.0, Claude Fable 5.2: Claude Code in --bare mode · max effort · 10 trials per task · no internet access · safeguards on
  2. Terminal-Bench 4.0, Claude Mythos 5.2: Claude Code in --bare mode · max effort · 10 trials per task · without safeguards
  3. 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
  4. Terminal-Bench Science 0.1, Claude Mythos 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 · without safeguards, per the system card · standard error ±4.3 points, per the system card
  5. 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
  6. 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
  7. SWE-bench Pro, Set not stated, Claude Fable 5.2: max effort · adaptive thinking · average of 5 trials
  8. 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
  9. OSWorld 2.1, Offline set (82 tasks), partial score, Claude Fable 5.2: highest available effort · safeguards on
  10. OSWorld 2.1, Offline set (82 tasks), strict pass rate, Claude Fable 5.2: max effort · mean of 5 attempts
  11. 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
  12. DeepSWE v1.1, Claude Fable 5.2: average of 5 trials
  13. ARC-AGI-3, Semi-Private set (55 environments), Claude Fable 5.2: Run by ARC Prize Foundation · Standard harness · high effort
  14. Chartography, No tools, Claude Fable 5.2: highest available effort · safeguards on
  15. 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

Related

All comparisons