Model lifecycle

Grok 4.5

Released 2026-07-08 · Back to Grok

Exact-version signals observed 2026-08-06–2026-09-03 · n=61

Data window: 2026-08-08 00:00:00 to 2026-09-05 00:00:00 UTC · Scoring method: experience_score_v2.

Trend history still collecting The current window is ready; 1 of 4 independent segments are available.

Lifecycle updated daily · latest complete UTC day 2026-09-04

Fixed 14-day baseline
73.1
n=34
Latest 28 days
60.5
n=59
Change vs baseline
−12.6
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 2026-09-05; latest score 60.3, fixed baseline 73.1.4050607080Fixed baseline 73.12026-07-31–2026-08-14 · 73.1 · n=342026-08-01–2026-08-15 · 73.8 · n=352026-08-02–2026-08-16 · 70.3 · n=372026-08-03–2026-08-17 · 70.3 · n=372026-08-04–2026-08-18 · 71.4 · n=392026-08-05–2026-08-19 · 72.8 · n=412026-08-06–2026-08-20 · 72.8 · n=412026-08-07–2026-08-21 · 72.1 · n=402026-08-08–2026-08-22 · 66.1 · n=422026-08-09–2026-08-23 · 64.6 · n=392026-08-10–2026-08-24 · 62.5 · n=362026-08-11–2026-08-25 · 60.3 · n=3308-1408-1808-2208-2608-3009-0309-05

1 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: General text, Coding.

Category Baseline → current Category change Weight share Experience contribution Discussion-mix contribution
General text Baseline → current54.0 → 46.2n=14 → 24 Category change−7.8 Weight share40.8% → 39.4% Experience contribution−3.13 Discussion-mix contribution+0.14
Coding Baseline → current70.7 → 66.9n=10 → 11 Category change−3.8 Weight share28.1% → 17.4% Experience contribution−0.87 Discussion-mix contribution−0.91
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
Reasoning Baseline → currentnot enough datan=6 → 7 Category change Weight share Experience contribution Discussion-mix contribution
Roleplay / creative Baseline → currentnot enough datan=0 → 5 Category change Weight share Experience contribution Discussion-mix contribution
Safety & refusals Baseline → currentnot enough datan=0 → 1 Category change Weight share Experience contribution Discussion-mix contribution
Speed & latency Baseline → currentnot enough datan=4 → 11 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: −7.83 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.