Model lifecycle

Claude Fable 5

Released 2026-06-09 · Back to Claude

Exact-version signals observed 2026-08-07–2026-08-27 · n=469

Trend history still collecting The current window is ready; 2 of 4 independent segments are available.

Lifecycle updated daily · latest complete UTC day 2026-08-27

Fixed 14-day baseline
57.5
n=196
Latest 28 days
57.3
n=469
Change vs baseline
−0.2
90-day slope
pts / 30 days

14-day rolling experience

Each daily point summarizes the previous 14 complete UTC days. The dashed line is the fixed release baseline; the verdict still uses independent non-overlapping 14-day segments.

14-day rolling experience from 2026-08-14 to 2026-08-28; latest score 56.9, fixed baseline 57.5.405060Fixed baseline 57.52026-07-31–2026-08-14 · 57.5 · n=1962026-08-01–2026-08-15 · 57.1 · n=2122026-08-02–2026-08-16 · 57.4 · n=2262026-08-03–2026-08-17 · 57.3 · n=2392026-08-04–2026-08-18 · 57.8 · n=2522026-08-05–2026-08-19 · 56.5 · n=2902026-08-06–2026-08-20 · 56.4 · n=3112026-08-07–2026-08-21 · 56.0 · n=3212026-08-08–2026-08-22 · 55.1 · n=3072026-08-09–2026-08-23 · 56.3 · n=2862026-08-10–2026-08-24 · 55.8 · n=2822026-08-11–2026-08-25 · 55.2 · n=2962026-08-12–2026-08-26 · 56.3 · n=2972026-08-13–2026-08-27 · 55.0 · n=2872026-08-14–2026-08-28 · 56.9 · n=27308-1408-1708-2008-2308-2608-28

2 of 4 independent 14-day segments ready for trend judgment.

What explains the change

Experience change and discussion-mix change are separated. These are observational contributions, not proof of cause.

Largest negative experience contributions: Safety & refusals.

Category Baseline → current Category change Weight share Experience contribution Discussion-mix contribution
Safety & refusals Baseline → current24.6 → 18.8n=24 → 49 Category change−5.8 Weight share13.0% → 11.3% Experience contribution−0.71 Discussion-mix contribution+0.62
Coding Baseline → current63.7 → 65.5n=23 → 64 Category change+1.8 Weight share12.7% → 14.5% Experience contribution+0.24 Discussion-mix contribution+0.13
General text Baseline → current46.7 → 48.0n=79 → 200 Category change+1.3 Weight share36.6% → 39.5% Experience contribution+0.48 Discussion-mix contribution−0.29
Reasoning Baseline → current80.5 → 83.7n=58 → 119 Category change+3.2 Weight share32.5% → 27.4% Experience contribution+0.96 Discussion-mix contribution−1.29
Image / vision Baseline → currentnot enough datan=0 → 0 Category change Weight share Experience contribution Discussion-mix contribution
Local deploy Baseline → currentnot enough datan=0 → 0 Category change Weight share Experience contribution Discussion-mix contribution
Roleplay / creative Baseline → currentnot enough datan=4 → 7 Category change Weight share Experience contribution Discussion-mix contribution
Speed & latency Baseline → currentnot enough datan=8 → 30 Category change Weight share Experience contribution Discussion-mix contribution
Video generation Baseline → currentnot enough datan=0 → 0 Category change Weight share Experience contribution Discussion-mix contribution

Unresolved contribution from categories below the sample threshold: −0.36 pts.

Lifecycle scores use the same experience-signal weights as the main index, without sample shrinkage after n=30. They measure public user perception, not model capability or backend causes.