Skip to main content

AnthropicOpenAILLM matchup

Claude Fable 5.2vs.GPT-6.2 Sol

Which one is better?

GPT-6.2 Sol does not have enough benchmark results yet. GPT-6.2 Sol is cheaper: Claude Fable 5.2 costs 4 times as much.

IntelligenceOverall index, 100 points = average
130.9

Claude Fable 5.2

Rank 1

n/a

GPT-6.2 Sol

not ranked yet

SpeedTokens per second
76

Claude Fable 5.2

n/a

GPT-6.2 Sol

GPT-6.2 Sol cheaper
Price$ per 1M tokens
$16

Claude Fable 5.2

$4

GPT-6.2 Sol

Popularity0 to 100
77

Claude Fable 5.2

Rank 27 of 511

n/a

GPT-6.2 Sol

With more than 272,000 input tokens, GPT-6.2 Sol costs more: $4 input and $15 output per 1M tokens.

Where is the difference?

Neither model is clearly ahead in any of the 8 areas.

too little data: 8

Areas in the overall index
Codingonly Fable 5.2 has a score
Reasoningonly Fable 5.2 has a score
Mathematicsonly Fable 5.2 has a score
Knowledgeonly Fable 5.2 has a score
Agentsonly Fable 5.2 has a score
Generalonly Fable 5.2 has a score
Specialist fields
Financeonly Fable 5.2 has a score
Legalonly Fable 5.2 has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Which model for which task?

Everyday tasks, translated from the area values above. Each row names the values it rests on.

Writing and debugging codeopenCoding without a score for GPT-6.2 Sol
Maths and data analysisopenMathematics without a score for GPT-6.2 Sol, Reasoning without a score for GPT-6.2 Sol
Facts and researchopenKnowledge without a score for GPT-6.2 Sol
Agents and workflowsopenAgents without a score for GPT-6.2 Sol
Many requests on a small budgetGPT-6.2 Sol$16 to $4 per 1M tokens
Finance, legal and medical textsopenFinance without a score for GPT-6.2 Sol, Legal without a score for GPT-6.2 Sol

Claude Fable 5.2 vs. GPT-6.2 Sol in our own test

The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Task origin: Simon Willison

Claude Fable 5.2

Not tested yet

GPT-6.2 Sol

Not tested yet

Popularity compared

How often the models are searched for, used and mentioned, on a scale from 0 to 100.

GPT-6.2 Sol has no popularity score yet.

Over time

The timeline appears once both models have two values.

All data side by side

The better value is bold. For the overall index only when the gap is clear.

MetricClaude Fable 5.2GPT-6.2 Sol
Intelligence
Overall indexpoints, 100 = reference group average, higher is better130.9n/a
RankRank 1 of 95not ranked yet
Price per 1M tokens
Inputwhat you send$8$2above 272,000 input tokens: $4
Outputwhat the model writes$40$10above 272,000 input tokens: $15
Speed
Tokens per second76n/a
Popularity
Popularitysearch, usage and mentions, 0 to 10077Rank 27 of 511n/a
Technical
Context windowsource-reported context limit1 M tokens≈ 1,500 A4 pages1.05 M tokens≈ 1,580 A4 pages
Knowledge cutoffJune 2026Jun 1, 2026
ReleasedNov 9, 2026Nov 17, 2026
AvailabilityActiveActive
Open weightsnono
  • Claude Fable 5.2, Batch pricing: $4 input and $20 output per million tokens, separate from standard API pricing. Source
  • Claude Fable 5.2, Fast pricing: $16 input and $80 output per million tokens. Fast is a separate serving mode. Source
  • GPT-6.2 Sol, 12-hour cache write price: The table lists the 30-minute rate. For 12-hour retention, OpenAI charges $5 per 1M tokens at the Standard rate through 272,000 input tokens. Source
  • GPT-6.2 Sol, Long-context pricing: Above 272,000 input tokens, the higher rates apply to the entire request. Source
  • GPT-6.2 Sol, Batch, Fast, and Ultrafast: Batch costs half the Standard rate and Fast costs twice the Standard rate. Ultrafast costs three times the Standard rate through February 28, 2027 and six times the rate from March 1, 2027. The change follows Pacific time. Source

Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis

Shared benchmarks

Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.

No directly comparable result yet

No published benchmark for Claude Fable 5.2 and GPT-6.2 Sol currently matches in version, task and metric. We therefore show no estimated or blended values.

More comparisons

Compare Claude Fable 5.2 and GPT-6.2 Sol with the models people compare them with most often.

Compare another matchup