Model results
GLM 5.3
Zhipu · Overall Models
- Score · relative 0–100
- 57.8
- Rank
- 5
- Status
- Partial 3/3
- Rank change
- Baseline
- Last tested
- 2026-09-10
- Settings tested
- All three benchmark settings tested
Why this result is partial: the official generation cohort is incomplete. The rank uses the available reasoning-setting results.
Scores by reasoning setting
| Tested setting | Score | Result status | Display group |
|---|---|---|---|
| Low | 35.1 | Tested and included | Baseline |
| High | 59.4 | Tested and included | Balanced |
| Max | 78.9 | Tested and included | Intensive |
Available settings and grouping
Available settings
LowHighMax
Checked on 2026-09-03 · Provider documentation
How settings are grouped
- Baseline: Low — tested and included
- Balanced: High — tested and included
- Intensive: Max — tested and included
Player program results
Max: 100% / 0% / 0% · n 7High: 75% / 25% / 0% · n 8Low: 100% / 0% / 0% · n 8 All three benchmark settings testedGeneration cost
- Average estimated cost
- $0.20
- Median estimated cost
- $0.16
- Estimated range
- $0.02–$0.53
- Cost data
- 24 combinations / 24 recorded runs
- Observed total
- $4.79
- Price source
- Provider-reported
- Price list
- Not recorded for this older data
- Average output
- 43k tokens
- Output range
- 2.7k–117k tokens
- Samples
- 24
Estimated cost gives equal weight to each model, game, and reasoning-setting combination.
Test setup
- Combines this model's tested reasoning settings
- Uses the standard GameBench player-program prompt