Model lifecycle

GPT-5.6 Sol

Released 2026-07-10 · Back to GPT

Exact-version signals observed 2026-08-07–2026-08-27 · n=401

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
56.1
n=120
Latest 28 days
49.5
n=401
Change vs baseline
−6.6
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 46.7, fixed baseline 56.1.405060Fixed baseline 56.12026-07-31–2026-08-14 · 56.1 · n=1202026-08-01–2026-08-15 · 54.7 · n=1372026-08-02–2026-08-16 · 54.6 · n=1472026-08-03–2026-08-17 · 52.9 · n=1612026-08-04–2026-08-18 · 49.3 · n=2002026-08-05–2026-08-19 · 50.4 · n=2532026-08-06–2026-08-20 · 51.1 · n=2642026-08-07–2026-08-21 · 51.1 · n=2702026-08-08–2026-08-22 · 50.2 · n=2652026-08-09–2026-08-23 · 50.6 · n=2792026-08-10–2026-08-24 · 47.2 · n=2992026-08-11–2026-08-25 · 45.6 · n=3152026-08-12–2026-08-26 · 46.9 · n=3122026-08-13–2026-08-27 · 46.7 · n=3092026-08-14–2026-08-28 · 46.7 · n=28108-1408-1708-2008-2308-2608-28

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: Coding, General text, Speed & latency.

Category Baseline → current Category change Weight share Experience contribution Discussion-mix contribution
Coding Baseline → current52.9 → 43.7n=26 → 76 Category change−9.1 Weight share22.5% → 19.7% Experience contribution−1.92 Discussion-mix contribution+0.12
General text Baseline → current45.6 → 39.9n=33 → 150 Category change−5.8 Weight share26.4% → 36.4% Experience contribution−1.81 Discussion-mix contribution−0.97
Speed & latency Baseline → current64.8 → 57.7n=25 → 69 Category change−7.1 Weight share19.1% → 16.6% Experience contribution−1.27 Discussion-mix contribution−0.21
Reasoning Baseline → current61.1 → 65.9n=32 → 82 Category change+4.8 Weight share28.9% → 21.5% Experience contribution+1.20 Discussion-mix contribution−0.82
Image / vision Baseline → currentnot enough datan=0 → 16 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=0 → 0 Category change Weight share Experience contribution Discussion-mix contribution
Safety & refusals Baseline → currentnot enough datan=4 → 8 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: −0.95 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.