Compare / Claude Fable 5 vs Claude Fable 5.1

Claude Fable 5 vs Claude Fable 5.1

Which is cheaper, which is more capable, and which does better at each kind of work, from 29 results on 8 sources that measured both models.

AnthropicClaude Fable 5 Released 9 Jun 2026 · $10.00 in · $50.00 out
AnthropicClaude Fable 5.1 Released 1 Sep 2026 · $10.00 in · $50.00 out
Claude Fable 5 wins 58 too close to callClaude Fable 5.1 wins 16

Of the 29 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee).

Claude Fable 5 or Claude Fable 5.1? The short answer

Claude Fable 5.1 is the newer version at about the same price, and it scores higher (Intelligence Index 53.4 against 49.6): upgrade.

  • They cost about the same: $20.00 and $20.00 per million tokens (three input to one output).
  • Claude Fable 5.1 scores higher on the Artificial Analysis Intelligence Index: 53.4 against 49.6.
  • Claude Fable 5.1 is newer: released 1 Sep 2026, against 9 Jun 2026 for Claude Fable 5.
  • On third-party benchmarks, on the results both models have: Claude Fable 5 does better for writing; Claude Fable 5.1 for agents and tool use, professional work, reasoning and knowledge and sticking to the facts.

Head to head

49.6
Intelligence Index
53.4
$20.00
Price per million tokens, blendedlower is better
$20.00
1,000,000
Context window, tokens
1,000,000

Every fact side by side

Claude Fable 5Claude Fable 5.1
Price per million tokens$10.00 in · $50.00 out$10.00 in · $50.00 out
Blended (3 in : 1 out)$20.00$20.00
Cheapest host, blended$20.00 (Amazon Bedrock)$20.00 (Amazon Bedrock)
Cached input, per million$1.00 cached input$0.25 cached input
Intelligence Index49.653.4
Spring Prompt overall–64
Output speed, tokens a second–72
Context window1,000,000 tokens1,000,000 tokens
Released9 Jun 20261 Sep 2026 (newer)
WeightsClosedClosed
Developer based inthe USthe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live not measured 24 of 32
Decks from an analysisTurning a finished analysis into a deck you could present as it is not measured 11 of 32
Marketing planningPlanning a year of ad spend without overspending not measured 10 of 32
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 22 of 159 19 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 6 of 51 4 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 12 of 187 5 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 2 of 169 19 of 169
Sticking to the factsSummarising without inventing things, and factual answers 7 of 139 5 of 139
Speed under pressureGood decisions against a real clock (fast chess) not measured 36 of 36

From our research

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureClaude Fable 5Claude Fable 5.1
APEX-Agents reported by APEX-Agents · 1 result
Tasks passed% of tasks, higher is better 9 · 3 of 37 measured 63.6% 68.6%
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 3 · 6 of 387 measured 1,504high reasoning 1,501max reasoning
Overall · Text factualityArena rating, higher is better 8 · 3 of 163 measured 1,484high reasoning 1,500max reasoning
Business, management and finance · TextArena rating, higher is better 5 · 17 of 380 measured 1,502high reasoning 1,484max reasoning
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 9 · 3 of 249 measured 49.6max reasoning 53.4max reasoning
GPQA Diamond% of questions, higher is better 19 · 8 of 232 measured 92.6%max reasoning 93.7%max reasoning
Humanity's Last Exam% of questions, higher is better 4 · 2 of 250 measured 55.5%max reasoning 59.1%max reasoning
GDP.pdf reported by GDP.pdf · 1 result
Professional document tasks% of rubric, higher is better 3 · 4 of 32 measured 30.0% 29.6%high reasoning
Remote Labor Index reported by Remote Labor Index · 1 result
Projects done to client standard% of projects, higher is better 3 · 2 of 13 measured 16.1% 17.9%
SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result
Correct answers% of questions, higher is better 6 · 5 of 76 measured 70.7%xhigh reasoning 70.8%max reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 3 · 31 of 230 measured 74.2high reasoning 63.9medium reasoning
Requested-length error · UGI% off the requested word count, lower is better 5 · 8 of 230 measured 2.0%high reasoning 3.0%high reasoning
Style adherence · UGIscore from 0 to 1, higher is better 9 · 2 of 230 measured 0.41xhigh reasoning 0.43high reasoning
Vending-Bench 2 reported by Vending-Bench 2 · 1 result
Money after a yearUS dollars, higher is better 19 · 22 of 58 measured $5,680high reasoning $5,422
Show all 29 results (15 more)
MeasureClaude Fable 5Claude Fable 5.1
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 9 results
Confirmed task success · AgentIPS effect estimate, higher is better 12 · 1 of 48 measured 0.06high reasoning, arena agent 0.18max reasoning, arena agent
Creative writing · TextArena rating, higher is better 3 · 9 of 385 measured 1,503high reasoning 1,482max reasoning
Expert prompts · TextArena rating, higher is better 2 · 15 of 338 measured 1,549high reasoning 1,521max reasoning
Instruction following · TextArena rating, higher is better 4 · 6 of 387 measured 1,509high reasoning 1,497max reasoning
Overall · DocumentArena rating, higher is better 1 · 4 of 38 measured 1,499 1,493max reasoning
Praise over complaint · AgentIPS effect estimate, higher is better 9 · 2 of 48 measured 0.17high reasoning, arena agent 0.32max reasoning, arena agent
Steerability · AgentIPS effect estimate, higher is better 5 · 6 of 48 measured 0.09high reasoning, arena agent 0.09max reasoning, arena agent
Tool grounding · AgentIPS effect estimate, higher is better 3 · 4 of 48 measured 0.00high reasoning, arena agent 0.00max reasoning, arena agent
Writing, literature and language · TextArena rating, higher is better 3 · 7 of 386 measured 1,508high reasoning 1,491max reasoning
Artificial Analysis reported by Artificial Analysis · 6 results
Terminal-Bench 2.1% of tasks, higher is better 13 · 1 of 131 measured 84.6%max reasoning 91.4%max reasoning
Terminal-Bench 4.0% of tasks, higher is better 12 · 8 of 120 measured 42.4%max reasoning 55.1%xhigh reasoning
τ-bench banking% of tasks, higher is better 23 · 8 of 121 measured 38.1%max reasoning 47.2%max reasoning
Artificial Analysis Coding Indexindex score, higher is better 7 · 1 of 130 measured 76.5max reasoning 81.6max reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 25 · 4 of 241 measured 82.3%max reasoning 85.3%max reasoning
SciCode% of problems, higher is better 4 · 2 of 121 measured 61.0%max reasoning 63.1%max reasoning

Quick answers

Is Claude Fable 5 better than Claude Fable 5.1?

Claude Fable 5.1 is the newer version at about the same price, and it scores higher (Intelligence Index 53.4 against 49.6): upgrade.

Which is cheaper, Claude Fable 5 or Claude Fable 5.1?

They cost about the same: $20.00 and $20.00 per million tokens (three input to one output).

Which is better for agents and tool use, Claude Fable 5 or Claude Fable 5.1?

Claude Fable 5.1 ranks 19 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 22 for Claude Fable 5.

Which is better for professional work, Claude Fable 5 or Claude Fable 5.1?

Claude Fable 5.1 ranks 4 of 51 models on sale for real tasks from banking, consulting and law, business documents and freelance projects, against 6 for Claude Fable 5.

Which is better for reasoning and knowledge, Claude Fable 5 or Claude Fable 5.1?

Claude Fable 5.1 ranks 5 of 187 models on sale for hard questions across science, maths and general knowledge, against 12 for Claude Fable 5.

Which is better for writing, Claude Fable 5 or Claude Fable 5.1?

Claude Fable 5 ranks 2 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 19 for Claude Fable 5.1.

Which is better for sticking to the facts, Claude Fable 5 or Claude Fable 5.1?

Claude Fable 5.1 ranks 5 of 139 models on sale for summarising without inventing things, and factual answers, against 7 for Claude Fable 5.

Run Claude Fable 5 and Claude Fable 5.1 on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.