Head-to-head comparison across 3benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Claude Fable 5
96
Claude Sonnet 4.5
65
Verified leaderboard positions: Claude Fable 5 #2 · Claude Sonnet 4.5 unranked
Pick Claude Fable 5 if you want the stronger benchmark profile. Claude Sonnet 4.5 only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Agentic
+29.9 difference
Coding
+8.4 difference
Knowledge
+8.6 difference
Claude Fable 5
Claude Sonnet 4.5
$10 / $50
$3 / $15
N/A
N/A
N/A
N/A
1M+
200K
Pick Claude Fable 5 if you want the stronger benchmark profile. Claude Sonnet 4.5 only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Claude Fable 5 is clearly ahead on the provisional aggregate, 96 to 65. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Fable 5's sharpest advantage is in agentic, where it averages 85.2 against 55.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 84.3% to 50%. Claude Sonnet 4.5 does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
Claude Fable 5 is also the more expensive model on tokens at $10.00 input / $50.00 output per 1M tokens, versus $3.00 input / $15.00 output per 1M tokens for Claude Sonnet 4.5. That is roughly 3.3x on output cost alone. Claude Fable 5 is the reasoning model in the pair, while Claude Sonnet 4.5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Claude Fable 5 gives you the larger context window at 1M+, compared with 200K for Claude Sonnet 4.5.
Claude Fable 5 is ahead on BenchLM's provisional leaderboard, 96 to 65. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 84.3% and 50%.
Claude Sonnet 4.5 has the edge for knowledge tasks in this comparison, averaging 83.4 versus 74.8. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Claude Fable 5 has the edge for coding in this comparison, averaging 85.6 versus 77.2. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Claude Fable 5 has the edge for agentic tasks in this comparison, averaging 85.2 versus 55.3. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.