Model lifecycle

GLM 5.2

Released 2026-06-16 · Back to GLM

Exact-version signals observed 2026-06-16–2026-07-24 · n=1,457

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

Lifecycle updated daily · latest complete UTC day 2026-07-24

Fixed 14-day baseline
66.5
n=756
Latest 28 days
67.4
n=851
Change vs baseline
+0.9
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 2026-06-30 to 2026-07-24; latest score 64.9, fixed baseline 66.5.4050607080Fixed baseline 66.52026-06-16–2026-06-30 · 66.5 · n=7562026-06-17–2026-07-01 · 67.7 · n=7042026-06-18–2026-07-02 · 68.7 · n=6752026-06-19–2026-07-03 · 69.3 · n=6172026-06-20–2026-07-04 · 70.2 · n=5932026-06-21–2026-07-05 · 71.8 · n=5222026-06-22–2026-07-06 · 71.1 · n=4832026-06-23–2026-07-07 · 70.9 · n=4482026-06-24–2026-07-08 · 71.1 · n=4472026-06-25–2026-07-09 · 70.3 · n=4482026-06-26–2026-07-10 · 68.3 · n=4822026-06-27–2026-07-11 · 68.3 · n=4892026-06-28–2026-07-12 · 68.9 · n=4552026-06-29–2026-07-13 · 69.0 · n=4152026-06-30–2026-07-14 · 68.6 · n=3922026-07-01–2026-07-15 · 65.6 · n=3652026-07-02–2026-07-16 · 64.4 · n=3432026-07-03–2026-07-17 · 63.3 · n=3752026-07-04–2026-07-18 · 63.7 · n=3712026-07-05–2026-07-19 · 62.1 · n=3952026-07-06–2026-07-20 · 61.5 · n=3992026-07-07–2026-07-21 · 60.7 · n=3972026-07-08–2026-07-22 · 61.6 · n=4142026-07-09–2026-07-23 · 63.9 · n=4102026-07-10–2026-07-24 · 64.9 · n=36206-3007-0507-1007-1507-2007-24

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: Reasoning, Coding.

Category Baseline → current Category change Weight share Experience contribution Discussion-mix contribution
Reasoning 85.7 → 79.8n=178 → 177 −6.0 25.4% → 22.0% −1.42 −0.56
Coding 78.5 → 72.7n=108 → 96 −5.9 15.0% → 12.0% −0.79 −0.27
Speed & latency 47.8 → 50.3n=198 → 211 +2.5 25.4% → 24.8% +0.62 +0.12
Local deploy 29.7 → 51.0n=44 → 47 +21.3 5.5% → 5.2% +1.14 +0.08
General text 67.0 → 71.2n=214 → 306 +4.2 26.8% → 34.3% +1.28 +0.20
Image / vision not enough datan=7 → 1
Roleplay / creative not enough datan=2 → 4
Safety & refusals not enough datan=6 → 10

Unresolved contribution from categories below the sample threshold: +0.47 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.