LLM Comparison

Claude Fable 5.2 vs Claude Sonnet 4.6: benchmark scores, pricing & comparison.

Side-by-side Claude Fable 5.2 vs Claude Sonnet 4.6 comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.

Verdict: Claude Fable 5.2 ranks higher (#1 vs #50) and wins 3 of 3 shared benchmarks; Claude Sonnet 4.6 costs less ($3.00/$15.0 vs $8.00/$40.0 per 1M tokens).

Rank #1 vs #50AskClash overall scores 87.7 vs 26.5.
Pricing $8.00/$40.0 vs $3.00/$15.0Input and output token prices per 1M tokens when published.
Proprietary vs ProprietaryAnthropic vs Anthropic.

Claude Fable 5.2 vs Claude Sonnet 4.6 benchmark comparison

Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.

MetricClaude Fable 5.2Claude Sonnet 4.6
Overall Score87.726.5
Leaderboard Rank#1#50
ACB91.4—
AA Intelligence Index65.024.7
AutomationBench-AA76.4—
RWT—6.0
Vibe Code Bench v1.193.851.5
HLE-Diamond80.2—
GPQA—89.9
SWE-bench—80.2
FrontierCode-AA 2.048.8—
SWE-Atlas62.1—
Terminal-Bench 4.059.6—
AA-Briefcase v1.1 (Elo)1784.71061.9
EnterpriseBench: CoreCraft68.2—
Finance Agent v2.169.5—
MKA Climb WSR56.6—
Chartography80.8—
GDP.pdf51.8—
Input Price (per 1M tokens)$8.00$3.00
Output Price (per 1M tokens)$40.0$15.0
Context Window1M200K
Benchmarks Published154

Claude Fable 5.2 vs Claude Sonnet 4.6 head-to-head charts

Claude Fable 5.2 leads 3 and Claude Sonnet 4.6 leads 0 of 3 shared benchmarks. Claude Sonnet 4.6 is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.

Claude Fable 5.2Claude Sonnet 4.6
Overall
87.7Claude Fable 5.2
26.5Claude Sonnet 4.6
AA Intelligence Index
65.0Claude Fable 5.2
24.7Claude Sonnet 4.6
Vibe Code Bench v1.1
93.8Claude Fable 5.2
51.5Claude Sonnet 4.6
AA-Briefcase v1.1 (Elo)
1784.7Claude Fable 5.2
1061.9Claude Sonnet 4.6
Claude Fable 5.2
Input$8.00
Output$40.0
Workload$16
Context1M
Claude Sonnet 4.6
Input$3.00
Output$15.0
Workload$6.00
Context200K

Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.

More Claude Fable 5.2 and Claude Sonnet 4.6 comparisons

Explore how Claude Fable 5.2 and Claude Sonnet 4.6 stack up against other top-ranked LLMs.

How to read this comparison

Benchmark scores

Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.

Token pricing

Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.

Coverage matters

Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.

This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.