GLM · Last 7 days
GLM 5.2
0–100 · higher means more positive community experience, not benchmark performance.
Updated 2026-09-08 18:27 UTC · 2026-09-01 – 2026-09-08 UTCAs of 2026-09-08 18:00:04 UTC, GLM 5.2 in the GLM family has 35 explicitly attributed community comments in the last 7 days; its community score is 71.8/100. Available category scores include General text 69.1/100 (n=14); Coding 61.9/100 (n=10); Reasoning 63.5/100 (n=6). Scoring method and sources
Explore long-term changes & analysis
Model lifecycle
GLM 5.2
Released 2026-06-16 · Back to GLM
Exact-version signals observed 2026-08-07–2026-09-07 · n=294
Data window: 2026-08-11 00:00:00 to 2026-09-08 00:00:00 UTC · Scoring method: experience_score_v2.
Lifecycle updated daily · latest complete UTC day 2026-09-07
- Fixed 14-day baseline
- 74.7 n=90
- Latest 28 days
- 66.7 n=244
- Change vs baseline
- −8.0
- 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.
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: General text, Speed & latency, Reasoning.
| Category | Baseline → current | Category change | Weight share | Experience contribution | Discussion-mix contribution |
|---|---|---|---|---|---|
| General text | Baseline → current69.3 → 62.6n=30 → 79 | Category change−6.6 | Weight share33.1% → 31.3% | Experience contribution−2.14 | Discussion-mix contribution+0.02 |
| Speed & latency | Baseline → current56.1 → 44.9n=16 → 43 | Category change−11.2 | Weight share17.8% → 17.2% | Experience contribution−1.96 | Discussion-mix contribution+0.09 |
| Reasoning | Baseline → current76.4 → 71.6n=21 → 55 | Category change−4.8 | Weight share24.7% → 23.1% | Experience contribution−1.16 | Discussion-mix contribution−0.12 |
| Coding | Baseline → current72.7 → 78.6n=20 → 54 | Category change+5.9 | Weight share21.3% → 23.3% | Experience contribution+1.31 | Discussion-mix contribution+0.17 |
| Image / vision | Baseline → currentnot enough datan=0 → 0 | Category change– | Weight share– | Experience contribution– | Discussion-mix contribution– |
| Local deploy | Baseline → currentnot enough datan=3 → 7 | 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=0 → 6 | 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: −4.24 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.
Community reviews
Selected comments from the last 7 days. The balance of excerpts does not represent the share of positive reviews.
3 selected excerpts
Show original
GLM5.2在workbuddy的回答如下：（摘录）重点： 全链路ID追踪的锚点： 识别出来或者暂存的作为原料，证据册根据证据清单排序，页码不会乱，不会漂移。 逐点回答你的五个层次
Show original
压缩国模glm5.2，性能直接低了十分，这就是蒸馏都不会蒸
Show original
同级别的 GLM-5.2 要 28 左右
No selected comments for this filter in the last 7 days.