Claude Fable 5 vs Claude Sonnet 5.5
Claude Fable 5 was superseded by Claude Fable 5.1. The grades below are the last ones measured, so read them as history rather than as this week's board. See the current roster.
Claude Fable 5 leads overall, C to C-. Claude Sonnet 5.5 is about 59x cheaper per task. By suite, real-world issues is even at C- and Claude Sonnet 5.5 takes spec planning (C+ to C). Take Claude Sonnet 5.5 anyway when you want the side that is cheaper per task, faster on real-world issues and ahead on spec planning.Measured
Each agent graded on the same private suites, running headless through its own tools. Advantages are oriented so a win is a win, whichever way the metric runs.
Verdict: Claude Sonnet 5.5 vs Claude Fable 5
Claude Fable 5 leads overall, C to C-. By suite: real-world issues is even at C- (60% vs 60% capability); Claude Sonnet 5.5 takes spec planning, C+ to C (74% vs 63% capability); Claude Fable 5 takes vibe coding, C+ to D+ (74% vs 48% capability). Claude Fable 5 used 7% of Claude Max 20x's weekly limit per pass, $0.169 per task at the listed price; at the ~$100 tier the board defaults to that is an estimated ~14% of Claude Max 5x's weekly limit (est, about $0.169 per task). Claude Sonnet 5.5 used <1% of Claude Max 5x's weekly limit per pass, $0.003 per task at the listed price. Per task, Claude Sonnet 5.5 is about 59x cheaper ($0.003 vs $0.169). Claude Sonnet 5.5 is faster on real-world issues: a median task takes 37s against 2m 37s. Both finished every task on it. Reasons to pick Claude Sonnet 5.5 anyway: it is cheaper per task ($0.003 vs $0.169), it is faster on real-world issues (37s vs 2m 37s median) and it leads on spec planning (C+ to C).
Changed since W35: Claude Fable 5: real-world issues C+ to C-, vibe coding C to C+.
| Dimension | Claude Fable 5 | Claude Sonnet 5.5 | Advantage |
|---|---|---|---|
| Capability | 60% | 60% | Even |
| Median task time | 2m 37s | 37s | 2m 0s faster (Claude Sonnet 5.5 leads) |
| Approx. task cost | $0.153 / task | $0.002 / task | $0.151 / task lower (Claude Sonnet 5.5 leads) |
Claude Fable 5: 33.0% of Claude Max 20x (33.0% / 5h, 5.0% / 1w) per run. Its weekly limit holds about 7 of the week's 33.6 5h windows. Claude Sonnet 5.5: 4.0% of Claude Max 5x (4.0% / 5h) per run. Its weekly limit holds about 13.8 of the week's 33.6 5h windows. Each figure is a share of that agent's own plan, so there is no delta to draw.
Work per window: Claude Fable 5 443 vs Claude Sonnet 5.5 3653 suite runs per month (Claude Sonnet 5.5 leads); per plan-dollar: 2.21 vs 36.52 (Claude Sonnet 5.5 leads). Work figures compare outputs, so unlike quota shares they are comparable across plans.
| Dimension | Claude Fable 5 | Claude Sonnet 5.5 | Advantage |
|---|---|---|---|
| Capability | 63% | 74% | +11% (Claude Sonnet 5.5 leads) |
| Median task time | 5m 32s | 3m 25s | 2m 7s faster (Claude Sonnet 5.5 leads) |
| Approx. task cost | $0.230 / task | $0.007 / task | $0.223 / task lower (Claude Sonnet 5.5 leads) |
Claude Fable 5: 10.0% of Claude Max 20x (10.0% / 5h, 2.0% / 1w) per run. Its weekly limit holds about 7 of the week's 33.6 5h windows. Claude Sonnet 5.5: 4.0% of Claude Max 5x (4.0% / 5h) per run. Its weekly limit holds about 13.8 of the week's 33.6 5h windows. Each figure is a share of that agent's own plan, so there is no delta to draw.
Work per window: Claude Fable 5 1461 vs Claude Sonnet 5.5 3653 suite runs per month (Claude Sonnet 5.5 leads); per plan-dollar: 7.30 vs 36.52 (Claude Sonnet 5.5 leads). Work figures compare outputs, so unlike quota shares they are comparable across plans.
| Dimension | Claude Fable 5 | Claude Sonnet 5.5 | Advantage |
|---|---|---|---|
| Capability | 74% | 48% | +26% (Claude Fable 5 leads) |
| Median task time | 5m 28s | 56s | 4m 32s faster (Claude Sonnet 5.5 leads) |
| Approx. task cost | $0.184 / task | $0.001 / task | $0.183 / task lower (Claude Sonnet 5.5 leads) |
Claude Fable 5: 2.8% of Claude Max 20x (2.8% / 5h, 0.4% / 1w) per good solve. Its weekly limit holds about 7 of the week's 33.6 5h windows. Claude Sonnet 5.5: 0.2% of Claude Max 5x (0.2% / 5h) per good solve. Its weekly limit holds about 13.8 of the week's 33.6 5h windows. Each figure is a share of that agent's own plan, so there is no delta to draw.
Work per window: Claude Fable 5 5218 vs Claude Sonnet 5.5 73050 good solves per month (Claude Sonnet 5.5 leads); per plan-dollar: 26.09 vs 730.50 (Claude Sonnet 5.5 leads). Work figures compare outputs, so unlike quota shares they are comparable across plans.
Grades and deltas are comparable only within a suite version. See methodology.
Frequently asked questions
Which is better for coding, Claude Fable 5 or Claude Sonnet 5.5?
They are even on our ladder: both clear tier 4 of 5 at 60% capability on real-world@v3, our private suite of real-world coding problems. Latest measurement 2026-08-30.
Which is cheaper per task, Claude Fable 5 or Claude Sonnet 5.5?
Claude Fable 5 used 7% of Claude Max 20x's weekly limit per pass, $0.169 per task at the listed price; at the ~$100 tier the board defaults to that is an estimated ~14% of Claude Max 5x's weekly limit (est, about $0.169 per task). Claude Sonnet 5.5 used <1% of Claude Max 5x's weekly limit per pass, $0.003 per task at the listed price. Per task, Claude Sonnet 5.5 is about 59x cheaper ($0.003 vs $0.169).
Which gives more coding work per dollar, Claude Fable 5 or Claude Sonnet 5.5?
Claude Sonnet 5.5 delivers more benchmark work per subscription dollar: 36.52 suite runs per plan-dollar versus 2.21 for Claude Fable 5 (at $100/month priced 2026-07-20, and $200/month priced 2026-08-05). Work figures compare outputs, so unlike raw quota shares they are comparable across plans.
What do Claude Fable 5 and Claude Sonnet 5.5 cost a month?
Claude Fable 5 runs on Claude Max 20x at $200/month (public price as of 2026-08-05). Claude Sonnet 5.5 runs on Claude Max 5x at $100/month (public price as of 2026-07-20).