Noometry

Anthropic, proprietary

Claude Fable 5.1

Claude Fable 5.1 by Anthropic ranks 2nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 69.0. Its strongest category is coding, where it ranks 1st. API pricing starts at $10 per million input tokens and $50 per million output tokens, with a 1M-token context window.

Last verified

Noometry rank
#2 of 354
Index score
69.0
Evidence
Confirmed 52 results
Provider
Anthropic
Released
September 1, 2026
Weights
Proprietary
Reasoning
Yes
Context window
1M
Max output
128K
Input price
$10 / M
Output price
$50 / M
Blended price
$20 / M
Output speed
Not measured
Value
#207 of 219
Knowledge cutoff
June 2026
Input
text, image, pdf

Category scores

Each category score combines every public result we have in that category.

  1. Coding 74.7
  2. Agentic & Tool Use 50.7
  3. Reasoning 76.7
  4. Math 89.6
  5. Knowledge 69.6
  6. Multimodal 53.9
  7. Multilingual 59.1
  8. Instruction Following 79.2
  9. Long Context 46.7
  10. Writing & Preference 79.2
CategoryScoreRankResults
Coding74.7#19
Agentic & Tool Use50.7#53
Reasoning76.7#710
Math89.6#45
Knowledge69.6#63
Multimodal53.9#43
Multilingual59.1#31
Instruction Following79.2#61
Long Context46.7#201
Writing & Preference79.2#24

Strengths and weaknesses

Categories where Claude Fable 5.1 places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Coding74.7+36.0#1 of 340, top 1%
Writing & Preference79.2+25.4#2 of 312, top 1%
Multilingual59.1+11.7#3 of 297, top 2%

Weakest categories

CategoryScorevs medianRank
Long Context46.7+5.8#20 of 296, top 7%
Agentic & Tool Use50.7+20.3#5 of 154, top 4%
Multimodal53.9+15.3#4 of 128, top 4%

Closest competitors

The models ranked just above and below Claude Fable 5.1. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
GPT-6 Astra#170.8$20—Compare
Claude Opus 5.5#368.6$8—Compare
Claude Opus 5#467.8$10—Compare
Claude Fable 5#566.8$2025Compare
GPT-6.1 Sol#665.6$4—Compare
GPT-5.6 Sol#765.0$810Compare
GPT-5.5 Pro#864.3$67.50—Compare
GPT-5.5#963.4$11.2525Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
FrontierCode50.9%#6 of 37, top 17%mediumEpoch AI
CursorBench49.2%highEpoch AI
CursorBench45.1%lowEpoch AI
CursorBench51.8%#3 of 14, top 22%maxEpoch AI
CursorBench46.8%mediumEpoch AI
CursorBench51.6%xhighEpoch AI
LMArena WebDev1744#5 of 113, top 5%LMArena2026-10-08
FrontierSWE56.3%#4 of 18, top 23%maxEpoch AI
SciCode57.6%highEpoch AI
SciCode55.7%lowEpoch AI
SciCode63.1%#2 of 121, top 2%maxEpoch AI
SciCode55.3%mediumEpoch AI
SciCode60.9%xhighEpoch AI
GSO88.2%Best of 31Epoch AI
WeirdML92.3%highEpoch AI
WeirdML92.9%#2 of 119, top 2%maxEpoch AI
LMArena Coding1528#6 of 294, top 3%LMArena2026-10-08
MirrorCode73.3%#2 of 9, top 23%highEpoch AI2026-09-10
ALE-Bench2,143#6 of 105, top 6%highEpoch AI

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
APEX-Agents68.6%#4 of 49, top 9%Epoch AI
APEX-Agents59.7%highEpoch AI
Remote Labor Index17.9%#2 of 14, top 15%Epoch AI
GDP.pdf29.6%#6 of 36, top 17%highEpoch AI
GDP.pdf27.6%maxEpoch AI
Vending-Bench 25,422#25 of 60, top 42%Epoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
ARC-AGI-288.8%highEpoch AI
ARC-AGI-278.3%lowEpoch AI
ARC-AGI-290%#6 of 83, top 8%maxEpoch AI
ARC-AGI-286.3%mediumEpoch AI
ARC-AGI-290%xhighEpoch AI
NYT Connections (extended)90%#18 of 91, top 20%high reasoningLech Mazur benchmarks
ARC-AGI-196%highEpoch AI
ARC-AGI-190%lowEpoch AI
ARC-AGI-197.5%#7 of 83, top 9%maxEpoch AI
ARC-AGI-194.5%mediumEpoch AI
ARC-AGI-196.5%xhighEpoch AI
CritPt30.3%highEpoch AI
CritPt27.7%lowEpoch AI
CritPt29.7%maxEpoch AI
CritPt29.1%mediumEpoch AI
CritPt31.1%#6 of 134, top 5%xhighEpoch AI
Chess Puzzles47%#12 of 129, top 10%maxEpoch AI2026-09-01
EBR-Bench57.1%#3 of 24, top 13%maxEpoch AI2026-09-08
LMArena Hard Prompts1526#5 of 297, top 2%LMArena2026-10-08
Mystery Game Puzzles58%#6 of 74, top 9%maxEpoch AI2026-09-01
DTBench97.6%#4 of 151, top 3%Epoch AI
DTBench96.5%highEpoch AI
DTBench94.1%lowEpoch AI
DTBench97.1%mediumEpoch AI
DTBench97.6%xhighEpoch AI
LMCA65.5%#2 of 125, top 2%Epoch AI
LMCA65.1%highEpoch AI
LMCA63.5%lowEpoch AI
LMCA65.3%mediumEpoch AI
LMCA65.1%xhighEpoch AI
Epoch Capabilities Index164.7#5 of 213, top 3%Epoch AI2026-09-01

Math

BenchmarkScorePositionSettingSourceDate
FrontierMath (Tiers 1-3)90.2%#4 of 81, top 5%maxEpoch AI2026-09-01
FrontierMath Tier 487.8%#6 of 63, top 10%maxEpoch AI2026-09-01
OTIS Mock AIME 2024-2025100%#2 of 173, top 2%maxEpoch AI2026-09-01
ProofBench100%Best of 77maxEpoch AI
LMArena Math1525#4 of 285, top 2%LMArena2026-10-08
FrontierMath Erdős0%#5 of 7, top 72%maxEpoch AI2026-09-01

Knowledge

BenchmarkScorePositionSettingSourceDate
Humanity's Last Exam46.5%#2 of 41, top 5%xhighEpoch AI
SimpleQA Verified70.8%#5 of 77, top 7%maxEpoch AI2026-09-01
LMArena Expert1535#7 of 273, top 3%LMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1318#4 of 122, top 4%LMArena2026-10-09
Blueprint-Bench 241.9%#4 of 31, top 13%Epoch AI
Furniture Assembly70%#5 of 31, top 17%maxEpoch AI2026-09-10
LMArena Document1513#2 of 38, top 6%LMArena2026-09-13

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1507#3 of 297, top 2%LMArena2026-10-08
LMArena Chinese1586#3 of 285, top 2%LMArena2026-10-08
LMArena French1525Best of 223LMArena2026-10-08
LMArena German1500#5 of 231, top 3%LMArena2026-10-08
LMArena Japanese1543Best of 211LMArena2026-10-08
LMArena Korean1534Best of 213LMArena2026-10-08
LMArena Russian1521#2 of 283, top 1%LMArena2026-10-08
LMArena Spanish1516#2 of 226, top 1%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1517#5 of 298, top 2%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1522#3 of 291, top 2%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1510#3 of 297, top 2%LMArena2026-10-08
LMArena Creative Writing1507#3 of 295, top 2%LMArena2026-10-08
EQ-Bench Creative Writing2162#2 of 115, top 2%EQ-Bench
LMArena Multi-Turn1492#9 of 295, top 4%LMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
anthropic$10$50$0.252026-10-10
azure$10$50$0.252026-10-10
bedrock$10$50$0.252026-10-10
openrouter$10$50$0.252026-10-10
vertex$10$50$0.252026-10-10

All Anthropic API prices → Estimate your cost →

Compare Claude Fable 5.1

Other Anthropic models

Frequently asked questions

How good is Claude Fable 5.1?

Claude Fable 5.1 by Anthropic ranks 2nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 69.0. Its strongest category is coding, where it ranks 1st. API pricing starts at $10 per million input tokens and $50 per million output tokens, with a 1M-token context window.

How much does Claude Fable 5.1 cost?

Claude Fable 5.1 costs $10 per million input tokens and $50 per million output tokens on Anthropic's own API, with cached input at $0.25.

What is Claude Fable 5.1's context window?

Claude Fable 5.1 accepts up to 1M tokens of input and can write up to 128K tokens in one response.

Is Claude Fable 5.1 open source?

No. Claude Fable 5.1 is proprietary and available only through Anthropic's API and partner platforms.

What are Claude Fable 5.1's strengths and weaknesses?

Relative to other ranked models, Claude Fable 5.1 places best in coding, writing & preference, multilingual and lowest in long context, agentic & tool use, multimodal.

What is Claude Fable 5.1 best at?

Its best category is coding, where it ranks 1st on Noometry.