Skip to content
Model Pareto

Claude Fable 5.2

AnthropicProprietaryanthropic.com ↗
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

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Claude Fable 5.2Estimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
MMMU-ProEstimated
~#3 of 88 (estimated)~86.6%
  1. #1Claude Opus 5.587.7%
  2. #2GPT-6 Astra86.9%
  3. ~#3Claude Fable 5.2Estimated86.6%
  4. #3GPT-6.1 Sol86.0%
No published score — estimated from related benchmarks
~#2 of 12 (estimated)~86.0%
  1. #1Gemini 3.8 Flash86.2%
  2. ~#2Claude Fable 5.2Estimated86.0%
  3. #2Kimi K384.8%
No published score — estimated from related benchmarks
~#2 of 8 (estimated)~91.2%
  1. #1MiniMax-M391.6%
  2. ~#2Claude Fable 5.2Estimated91.2%
  3. #2Kimi K391.1%
No published score — estimated from related benchmarks

Hard reasoning

GPQA DiamondEstimated
~#2 of 193 (estimated)~96.0%
  1. #1GPT-6 Astra96.1%
  2. ~#2Claude Fable 5.2Estimated96.0%
  3. #2Gemini 3.8 Flash95.3%
No published score — estimated from related benchmarks
AIME (latest)Estimated
~#2 of 34 (estimated)~99.0%
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Claude Fable 5.2Estimated99.0%
  3. #2Beam 1.0 501B A23B97.7%
No published score — estimated from related benchmarks
~#2 of 103 (estimated)~58.7
  1. #1Gemini 4 Carbon59.4
  2. ~#2Claude Fable 5.2Estimated58.7
  3. #2Claude Opus 5.557.6
No published score — estimated from related benchmarks

Agents

~#3 of 120 (estimated)~98.2%
  1. #1Step 3.7 Flash98.5%
  2. #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
  3. ~#3Claude Fable 5.2Estimated98.2%
  4. #3Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
~#2 of 15 (estimated)~84.4%
  1. #1Kimi K384.8%
  2. ~#2Claude Fable 5.2Estimated84.4%
  3. #2Qwen3.8 27B84.3%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#2 of 5 (estimated)~58.6%
  1. #1GLM-5.3 Flash59.1%
  2. ~#2Claude Fable 5.2Estimated58.6%
  3. #2Kimi K358.3%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#2 of 22 (estimated)~92.2%
  1. #1Atria Dawn Preview92.5%
  2. ~#2Claude Fable 5.2Estimated92.2%
  3. #2GPT-6 Astra91.5%
No published score — estimated from related benchmarks
~#2 of 91 (estimated)~50.4%
  1. #1Muse Spark 1.350.5%
  2. ~#2Claude Fable 5.2Estimated50.4%
  3. #2GLM-5.350.3%
No published score — estimated from related benchmarks