Electricity Bench

claude-fable-5 vs claude-sonnet-5

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.

claude-fable-5Clears tier 4 (partial tier 5) at 34.0% of Claude Max 20x per runCOVERALLclaude-sonnet-5Clears tier 2 (partial tier 5) at 6.0% of Claude Max 20x per runDOVERALL
real-world@v3CvsD
Dimensionclaude-fable-5claude-sonnet-5Advantage
Capability60%50%+10% (claude-fable-5 leads)
Median task time3m 12s4m 22s1m 10s faster (claude-fable-5 leads)
Approx. task cost$0.031 / task$0.005 / task$0.026 / task lower (claude-sonnet-5 leads)

claude-fable-5: 34.0% of Claude Max 20x (34.0% / 5h, 5.0% / 1w) per run. claude-sonnet-5: 6.0% of Claude Max 20x (6.0% / 5h, 1.0% / 1w) per run. Each figure is a share of that agent's own plan, so there is no delta to draw.

Work per window: claude-fable-5 430 vs claude-sonnet-5 2435 suite runs per month (claude-sonnet-5 leads); per plan-dollar: 2.15 vs 12.18 (claude-sonnet-5 leads). Work figures compare outputs, so unlike quota shares they are comparable across plans.

spec-planning@v1CvsD
Dimensionclaude-fable-5claude-sonnet-5Advantage
Capability64%39%+25% (claude-fable-5 leads)
Median task time5m 54s4m 38s1m 17s faster (claude-sonnet-5 leads)
Approx. task cost$0.041 / task$0.010 / task$0.031 / task lower (claude-sonnet-5 leads)

claude-fable-5: 12.0% of Claude Max 20x (12.0% / 5h, 1.0% / 1w) per run. claude-sonnet-5: 3.0% of Claude Max 20x (3.0% / 5h) per run. Each figure is a share of that agent's own plan, so there is no delta to draw.

Work per window: claude-fable-5 1218 vs claude-sonnet-5 4870 suite runs per month (claude-sonnet-5 leads); per plan-dollar: 6.09 vs 24.35 (claude-sonnet-5 leads). Work figures compare outputs, so unlike quota shares they are comparable across plans.

vibe-coding@v1CvsF
Dimensionclaude-fable-5claude-sonnet-5Advantage
Capability69%34%+35% (claude-fable-5 leads)
Median task time5m 25s5m 17s8s faster (claude-sonnet-5 leads)
Approx. task cost$0.038 / task$0.008 / task$0.030 / task lower (claude-sonnet-5 leads)

claude-fable-5: 2.8% of Claude Max 20x (2.8% / 5h, 0.6% / 1w) per good solve. claude-sonnet-5: 0.6% of Claude Max 20x (0.6% / 5h) per good solve. 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 24350 good solves per month (claude-sonnet-5 leads); per plan-dollar: 26.09 vs 121.75 (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 or claude-sonnet-5?

claude-fable-5 clears higher: tier 4 of 5 versus tier 2 for claude-sonnet-5 on real-world@v3, our private suite of real-world coding problems. Latest measurement 2026-08-17.

Which gives more work per dollar, claude-fable-5 or claude-sonnet-5?

claude-sonnet-5 delivers more benchmark work per subscription dollar: 12.18 suite runs per plan-dollar versus 2.15 for claude-fable-5 (at $200/month priced 2026-08-05, and $200/month priced 2026-08-05). Work figures compare outputs, so unlike raw quota shares they are comparable across plans.

How much do claude-fable-5 and claude-sonnet-5 cost?

claude-fable-5 runs on Claude Max 20x at $200/month (public price as of 2026-08-05). claude-sonnet-5 runs on Claude Max 20x at $200/month (public price as of 2026-08-05).