Claude Fable 5.1 vs Claude Sonnet 5
Claude Sonnet 5 is no longer on the leaderboard. 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 5.1 leads overall, B- to D. Claude Sonnet 5 is about 4.0x cheaper per task. By suite, Claude Fable 5.1 takes real-world issues (B+ to D+) and spec planning (C+ to D). Take Claude Sonnet 5 anyway when you want the side that is cheaper per task and faster on real-world issues.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 vs Claude Fable 5.1
Claude Fable 5.1 leads overall, B- to D. By suite: Claude Fable 5.1 takes real-world issues, B+ to D+ (87% vs 53% capability); Claude Fable 5.1 takes spec planning, C+ to D (71% vs 44% capability); Claude Fable 5.1 takes vibe coding, C+ to F (74% vs 31% capability). Claude Fable 5.1 used 8% of Claude Max 5x's weekly limit per pass, $0.097 per task at the listed price. Claude Sonnet 5 used 2% of Claude Max 5x's weekly limit per pass, $0.024 per task at the listed price. Per task, Claude Sonnet 5 is about 4.0x cheaper ($0.024 vs $0.097). Claude Sonnet 5 is faster on real-world issues: a median task takes 3m 35s against 3m 38s. Both finished every task on it. Reasons to pick Claude Sonnet 5 anyway: it is cheaper per task ($0.024 vs $0.097) and it is faster on real-world issues (3m 35s vs 3m 38s median).
Changed since W39: Claude Fable 5.1: real-world issues D+ to B+, real-world issues usage 7% to 5% of the weekly limit, spec planning usage 4% to 3% of the weekly limit, vibe coding C- to C+, vibe coding usage 0.6% to 0.4% of the weekly limit; Claude Sonnet 5: vibe coding D+ to F.
| Dimension | Claude Fable 5.1 | Claude Sonnet 5 | Advantage |
|---|---|---|---|
| Capability | 87% | 53% | +33% (Claude Fable 5.1 leads) |
| Median task time | 3m 38s | 3m 35s | 2s faster (Claude Sonnet 5 leads) |
| Approx. task cost | $0.077 / task | $0.015 / task | $0.061 / task lower (Claude Sonnet 5 leads) |
Claude Fable 5.1: 64.0% of Claude Max 5x (64.0% / 5h, 5.0% / 1w) per run. Its weekly limit holds about 13.8 of the week's 33.6 5h windows. Claude Sonnet 5: 12.0% of Claude Max 5x (12.0% / 5h, 1.0% / 1w) 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 5.1 228 vs Claude Sonnet 5 1218 suite runs per month (Claude Sonnet 5 leads); per plan-dollar: 2.28 vs 12.18 (Claude Sonnet 5 leads). Work figures compare outputs, so unlike quota shares they are comparable across plans.
| Dimension | Claude Fable 5.1 | Claude Sonnet 5 | Advantage |
|---|---|---|---|
| Capability | 71% | 44% | +27% (Claude Fable 5.1 leads) |
| Median task time | 8m 55s | 5m 12s | 3m 43s faster (Claude Sonnet 5 leads) |
| Approx. task cost | $0.172 / task | $0.057 / task | $0.115 / task lower (Claude Sonnet 5 leads) |
Claude Fable 5.1: 33.0% of Claude Max 5x (33.0% / 5h, 3.0% / 1w) per run. Its weekly limit holds about 13.8 of the week's 33.6 5h windows. Claude Sonnet 5: 5.0% of Claude Max 5x (5.0% / 5h, 1.0% / 1w) 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 5.1 443 vs Claude Sonnet 5 2922 suite runs per month (Claude Sonnet 5 leads); per plan-dollar: 4.43 vs 29.22 (Claude Sonnet 5 leads). Work figures compare outputs, so unlike quota shares they are comparable across plans.
| Dimension | Claude Fable 5.1 | Claude Sonnet 5 | Advantage |
|---|---|---|---|
| Capability | 74% | 31% | +43% (Claude Fable 5.1 leads) |
| Median task time | 4m 14s | 4m 31s | 17s faster (Claude Fable 5.1 leads) |
| Approx. task cost | $0.092 / task | $0.007 / task | $0.085 / task lower (Claude Sonnet 5 leads) |
Claude Fable 5.1: 4.2% of Claude Max 5x (4.2% / 5h, 0.4% / 1w) per good solve. Its weekly limit holds about 13.8 of the week's 33.6 5h windows. Claude Sonnet 5: 1.0% of Claude Max 5x (1.0% / 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 5.1 3479 vs Claude Sonnet 5 14610 good solves per month (Claude Sonnet 5 leads); per plan-dollar: 34.79 vs 146.10 (Claude Sonnet 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 5.1 or Claude Sonnet 5?
Claude Fable 5.1 clears higher: tier 4 of 5 versus tier 3 for Claude Sonnet 5 on real-world@v3, our private suite of real-world coding problems. Latest measurement 2026-09-27.
Which is cheaper per task, Claude Fable 5.1 or Claude Sonnet 5?
Claude Fable 5.1 used 8% of Claude Max 5x's weekly limit per pass, $0.097 per task at the listed price. Claude Sonnet 5 used 2% of Claude Max 5x's weekly limit per pass, $0.024 per task at the listed price. Per task, Claude Sonnet 5 is about 4.0x cheaper ($0.024 vs $0.097).
Which gives more coding work per dollar, Claude Fable 5.1 or Claude Sonnet 5?
Claude Sonnet 5 delivers more benchmark work per subscription dollar: 12.18 suite runs per plan-dollar versus 2.28 for Claude Fable 5.1 (at $100/month priced 2026-07-20, and $100/month priced 2026-07-27). Work figures compare outputs, so unlike raw quota shares they are comparable across plans.
What do Claude Fable 5.1 and Claude Sonnet 5 cost a month?
Claude Fable 5.1 runs on Claude Max 5x at $100/month (public price as of 2026-07-27). Claude Sonnet 5 runs on Claude Max 5x at $100/month (public price as of 2026-07-20).