Claude Fable 5 vs Claude Sonnet 5: Which Is Better for Coding? (2026)

head-to-head

Metric	Claude Fable 5	Claude Sonnet 5
SWE-bench Verified	95.0%	85.2%
SWE-bench Pro	80.3%	63.2%
Terminal-Bench	—	80.4% (TB2.1)
Input $ / 1M	$10	$2
Context	1M	1M
Open weights	No	No
Maker	Anthropic	Anthropic

when to pick each

Pick Claude Fable 5 if

Mythos-class flagship for long-horizon agentic runs: the model to reach for when a task spans hours and hundreds of tool calls and has to actually finish.

Pick Claude Sonnet 5 if

The best closed-model value — near-Opus scores at ~2.5× less, and the default daily driver for most developers.

Full reviewsClaude Fable 5, decoded Claude Sonnet 5, decoded

Ranked on our AI Coding Leaderboard, updated 2026-07-03. Scores are confirmed against primary sources; prices are per 1M input tokens and can change.

Primary sources

AnthropicGENZ TECH — Claude Fable 5 returns — SWE-bench Verified 95.0% (vals.ai independent eval) is the highest confirmed score of any model. SWE-bench Pro 80.3% uses Anthropic's own scaffolding and is contested. Restored Jul 1, 2026 after a 20-day export-control suspension. Pricing $10/$50 per 1M.
AnthropicGENZ TECH — Claude Sonnet 5, decoded — Anthropic-reported. Intro pricing $2/$10 per 1M through Aug 31, 2026, then $3/$15.
BenchmarkSWE-bench — the real-GitHub-issue benchmark

$ quick-answers

Is Claude Fable 5 better than Claude Sonnet 5 for coding?

Claude Fable 5 scores higher on SWE-bench Verified (95.0% vs 85.2%) and SWE-bench Pro, so it is the stronger coder on current benchmarks. Claude Sonnet 5 wins on price.

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

Claude Sonnet 5 is cheaper at $2 per 1M input tokens versus $10.

Should I use Claude Fable 5 or Claude Sonnet 5?

Claude Fable 5 for the hardest, highest-stakes coding; Claude Sonnet 5 when you want the best value or are running high volume. Both are frontier-class in 2026.