Claude Fable 5.2
- Input
- $8.00/M tok
- Output
- $40/M tok
- Blended
- $16/M tok · 3:1
- Speed
- ~48tok/sest.
- Context
- 1Mtokens
- Cost per task
- $27/task · AA
Rankings
Coding
Mixed#1 / 137rank by quality95.1±5.1quality / 1004/7 benchmarks measuredPrice frontierVision
Mixed#4 / 98rank by quality92.6±7.5quality / 1002/6 benchmarks measuredHard reasoning
Verified#1 / 218rank by quality99.6±4.3quality / 1001/4 benchmarks measuredPrice frontierAgents
Verified#3 / 187rank by quality97.6±5.1quality / 1002/7 benchmarks measured
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#2 of 21 (estimated)~94.9%
No published score — estimated from related benchmarks
DeepSWE v1.1Lab-reported
#5 of 4574.3%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #4Muse Wonder75.8%
- #5Claude Fable 5.274.3%
- #6DeepSeek V4.1 Flash74.2%
anthropic.com · 2026-11-09
LiveCodeBenchEstimated
~#2 of 28 (estimated)~92.3%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#5 of 26 (estimated)~57.8
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #4Muse Wonder Full58.9
- ~#5Claude Fable 5.2Estimated57.8
- #5Claude Fable 5.157.6
No published score — estimated from related benchmarks
Vision
CharXiv ReasoningEstimated
~#2 of 12 (estimated)~86.0%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#2 of 8 (estimated)~91.2%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#9 of 4724.2%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #8GPT-6 Sol24.8%
- #9Claude Fable 5.224.2%
- #10GPT-5.6 Terra24.0%
artificialanalysis.ai · 2026-11-10
Hard reasoning
GPQA DiamondEstimated
~#2 of 193 (estimated)~96.0%
No published score — estimated from related benchmarks
AIME (latest)Estimated
~#2 of 34 (estimated)~99.0%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#2 of 103 (estimated)~58.7
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Estimated
~#3 of 120 (estimated)~98.2%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- ~#3Claude Fable 5.2Estimated98.2%
- #3Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#2 of 15 (estimated)~84.4%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#2 of 5 (estimated)~58.6%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#2 of 22 (estimated)~92.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#2 of 91 (estimated)~50.4%
No published score — estimated from related benchmarks