ResearchLLM Verifications Leaderboard

Data as of · 78 models, 80 questions · reviewed by Suhas Bhairav · methodology

Head to head · tested 27 Oct 2026

Claude Fable 5.1 vs Claude Sonnet 5.5: accuracy, speed and price

Similar accuracy; Claude Sonnet 5.5 costs less per question.

AnthropicClaude Fable 5.181.2% score · #5$0.016 per question70 tok/sAnthropicClaude Sonnet 5.578.8% score · #7$0.0054 per question126 tok/s

Verdict

Built from the measurements below

  • Accuracy is too close to call: Claude Fable 5.1 scored 81.2% and Claude Sonnet 5.5 78.8% on the same 80 questions, a gap within what chance alone could produce.
  • Claude Sonnet 5.5 is 3.0× cheaper per question as billed ($0.0054 vs $0.016), reasoning tokens included.
  • Claude Sonnet 5.5 generates text 1.8× faster: 126 tokens per second against 70.
  • Claude Sonnet 5.5 starts answering sooner: 0.7 s to the first token, against 2.1 s for Claude Fable 5.1.

Which should you choose?

Choose Claude Fable 5.1 for shorter outputs (about 238 tokens per question against 456). Choose Claude Sonnet 5.5 for the lower cost per correct answer ($0.0069 against $0.02), faster streaming and a quicker first token. The widest subject gap is in law: Claude Fable 5.1 answered 5 of 6 correctly, Claude Sonnet 5.5 3 of 6. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.

Accuracy gap +2.5 points (z = 0.40). A winner is called only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.

Head to head

Same questions, same prompt, same API

MeasureClaude Fable 5.1Claude Sonnet 5.5Edge
Verification scoreHigher is better81.2%78.8%Too close to call
Cost per questionLower is better$0.016$0.0054Claude Sonnet 5.5
Output speedHigher is better70126Claude Sonnet 5.5
Time to first tokenLower is better2.1 s0.7 sClaude Sonnet 5.5
End-to-end response timeLower is better11.0 s6.2 sClaude Sonnet 5.5
Tokens per questionLower is better238456Claude Fable 5.1
Context windowHigher is better1M1MSimilar

Side by side

Bars are scaled to the larger of the two values. The winner on each measure is marked in bold.

Every measure

Claude Fable 5.1 first, Claude Sonnet 5.5 second

Verification scorehigher is better
Claude Fable 5.181.2%
Claude Sonnet 5.578.8%
Cost per questionlower is better
Claude Fable 5.1$0.016
Claude Sonnet 5.5$0.0054
Output speedhigher is better
Claude Fable 5.170
Claude Sonnet 5.5126
Time to first tokenlower is better
Claude Fable 5.12.1 s
Claude Sonnet 5.50.7 s
End-to-end response timelower is better
Claude Fable 5.111.0 s
Claude Sonnet 5.56.2 s
Tokens per questionlower is better
Claude Fable 5.1238
Claude Sonnet 5.5456
Context windowhigher is better
Claude Fable 5.11M
Claude Sonnet 5.51M

Score vs. cost per question

Both models in color, every other model in grey

Most attractive quadrant0255075100$0.00001$0.0001$0.001$0.01$0.10Cost per question (USD, log) →Verification score (%) →Qwen3.8 2.4T A95BCommand AReka Flash 3Gemma 4 26B A4BGemma 4 31BQwen3.5 397B A17BHermes 4 405BClaude Fable 5.1Grok 4.7o3gpt-oss-20bMinistral 3 3B 2512Nova Micro 1.0Phi 4Granite 4.2 8BHy3GLM 5.3 FlashSolar Pro 4Trinity Large ThinkingMiniMax M3Mistral Large 4Claude Opus 5.5GPT-6.1 SolGPT-6 Lunagpt-oss-120bLlama 4 MaverickQwen3.8 Max (0902)

Specifications and pricing

From OpenRouter's catalogue, plus the leaderboard's test dates

SpecificationClaude Fable 5.1Claude Sonnet 5.5
CreatorAnthropicAnthropic
Released1 Sept 202628 Sept 2026
Weights——
ReasoningYesYes
Inputtext, image, filetext, image, file
Outputtexttext
Context window1M tokens1M tokens
Knowledge cutoff——
List price in / out per 1M$10 / $50$2 / $10
Blended price per 1M (3:1)$20.00$4.00
Cheapest hostAzure · $10 / $50Google · $2 / $10
Hosts on OpenRouter45
Last tested27 Oct 202625 Oct 2026

Compare any two models →

Claude Fable 5.1 vs Claude Sonnet 5.5: frequently asked questions

Is Claude Fable 5.1 better than Claude Sonnet 5.5?
On accuracy they are statistically tied: Claude Fable 5.1 scored 81.2% and Claude Sonnet 5.5 78.8% on the same 80 questions from open datasets. Similar accuracy; Claude Sonnet 5.5 costs less per question.
Which is cheaper, Claude Fable 5.1 or Claude Sonnet 5.5?
Claude Sonnet 5.5 is cheaper: $0.0054 per question as billed, against $0.016. List prices: Claude Fable 5.1 $10 in / $50 out, Claude Sonnet 5.5 $2 in / $10 out per million tokens.
Which is faster, Claude Fable 5.1 or Claude Sonnet 5.5?
Claude Sonnet 5.5 is faster at 126 output tokens per second, against 70. Time to first token: 2.1 s for Claude Fable 5.1, 0.7 s for Claude Sonnet 5.5.
Which has the larger context window, Claude Fable 5.1 or Claude Sonnet 5.5?
Both accept about the same amount of context: 1M and 1M tokens.