Data points: 101
Model compare
The readout for GLM-4.5 Air and GLM-5, before the detailed comparison sheet.
Weighted outcome: GLM-5. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
GLM-5
GLM-5 has the higher weighted result; Model A / B score 40.7 to 59.3.
Evidence depth
101 data points
Includes 17 benchmark rows, 0 audit samples, and 8 provider examples.
Selection signal
Start with GLM-5
The charts below split 25 high-signal samples across speed, scores, and audit health.
Switch either side of this report to compare another model with the same LMSpeed data pipeline.
Select a different model to open a new comparison URL.
This report only uses LMSpeed data for GLM-4.5 Air and GLM-5: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | GLM-4.5 Air | GLM-5 |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 40.7 pts | 59.3 pts |
| Benchmark category leads | 2 categories | 4 categories |
| Operational advantages | Cheapest input price, Average speed, First-token latency | Provider coverage |
| Context window | 131.1K tokens | 204.8K tokens |
| Max output | 98.3K tokens | 131.1K tokens |
| Modalities | Input Text Output Text | Input Text |
The overall result weights benchmark capability categories at 80% and price, API speed/latency, and availability at 20%. Recent test volume does not affect the winner, and missing benchmark categories are excluded.
| Model compare | GLM-4.5 Air | GLM-5 |
|---|---|---|
| Developer | Z.ai | Z.ai |
| Released | Jul 2025 | Feb 2026 |
| Parameters | No data | No data |
| Tokenizer | Other | Other |
| Knowledge cutoff | 2024-12-31 | No data |
| OpenRouter ID | z-ai/glm-4.5-air | z-ai/glm-5 |
| References | No data | No data |
This report only uses LMSpeed data for GLM-4.5 Air and GLM-5: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
GLM-4.5 Air
GLM-4.5 Air is stronger in benchmark categories (Agents, Math) and operational dimensions (Cheapest input price, Average speed, First-token latency).
GLM-5
GLM-5 is stronger in benchmark categories (Coding, Reasoning, Knowledge, Instruction following) and operational dimensions (Provider coverage).
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
Compare benchmark category scores on a 0-100 scale. Select a category to inspect the gap.
Avg. score
GLM-4.5 Air
45.9
Avg. score
GLM-5
47.8
GLM-4.5 Air leads by 0.4
GLM-5 leads by 3.3
GLM-5 leads by 1.8
GLM-5 leads by 6.7
GLM-4.5 Air leads by 5.9
GLM-5
No data
GLM-5 leads by 10.0
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
GLM-4.5 Air
winner$0.170/M
Rank #23/162 · confidence 4
GLM-5
$1.00/M
Rank #98/162 · confidence 4
GLM-4.5 Air
winner$0.372/M
Rank #31/162 · confidence 4
GLM-5
$1.55/M
Rank #93/162 · confidence 4
GLM-4.5 Air
winner$0.980/M
Rank #39/162 · confidence 4
GLM-5
$3.20/M
Rank #89/162 · confidence 4
GLM-4.5 Air
81.5%
Rank #53/125 · confidence 4
GLM-5
winner85.7%
Rank #23/125 · confidence 4 · eval date 2026-03-01
GLM-4.5 Air
6.8%
Rank #116/187 · confidence 4
GLM-5
winner27.2%
Rank #38/187 · confidence 4
GLM-4.5 Air
43.7
Rank #74/89 · confidence 1 · eval date 2025-06-01
GLM-5
winner63.3
Rank #52/89 · confidence 4 · eval date 2026-03-01
GLM-4.5 Air
73.3%
Rank #106/188 · confidence 4
GLM-5
winner82.0%
Rank #67/188 · confidence 4
GLM-4.5 Air
30.6%
Rank #136/185 · confidence 4
GLM-5
winner46.2%
Rank #32/185 · confidence 4
GLM-4.5 Air
30.6
Rank #85/96 · confidence 1 · eval date 2025-06-01
GLM-5
winner46.2
Rank #36/96 · confidence 4 · eval date 2026-03-01
GLM-4.5 Air
winner92.3
Rank #7/90 · confidence 1 · eval date 2025-06-01
GLM-5
34.0
Rank #80/90 · confidence 4 · eval date 2026-03-01
GLM-4.5 Air
16.5
Rank #80/99 · confidence 1 · eval date 2025-06-01
GLM-5
winner39.5
Rank #34/99 · confidence 4 · eval date 2026-03-01
GLM-4.5 Air
6.8
Rank #75/96 · confidence 1 · eval date 2025-06-01
GLM-5
winner27.2
Rank #37/96 · confidence 4 · eval date 2026-03-01
GLM-4.5 Air
15.5
Rank #82/90 · confidence 1 · eval date 2025-06-01
GLM-5
winner26.9
Rank #48/90 · confidence 4 · eval date 2026-03-01
GLM-4.5 Air
73.3
Rank #74/96 · confidence 1 · eval date 2025-06-01
GLM-5
winner82.0
Rank #56/96 · confidence 4 · eval date 2026-03-01
GLM-4.5 Air
1171.0
Rank #48/66 · confidence 1 · eval date 2025-06-01
GLM-5
winner1274.0
Rank #23/66 · confidence 4 · eval date 2026-03-01
GLM-4.5 Air
37.6
Rank #77/86 · confidence 1 · eval date 2025-06-01
GLM-5
winner72.3
Rank #33/86 · confidence 4 · eval date 2026-03-01
GLM-4.5 Air
46.5
Rank #69/84 · confidence 1 · eval date 2025-06-01
GLM-5
winner98.2
Rank #6/84 · confidence 4 · eval date 2026-03-01
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GLM-4.5 Air | GLM-5 |
|---|---|---|
| No completed audits are available from shared providers yet. | ||
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | GLM-4.5 Air | GLM-5 |
|---|---|---|
60 tests | GLM-4.5 Air speed / latency 77 tok/s / 8245ms input / output No data | GLM-5 speed / latency 37 tok/s / 26385ms input / output No data |
25 tests | GLM-4.5 Air speed / latency 86 tok/s / 387ms input / output No data | GLM-5 speed / latency 44 tok/s / 27770ms input / output No data |
10 tests | GLM-4.5 Air speed / latency 20 tok/s / 33054ms input / output No data | GLM-5 speed / latency N/A / N/A input / output No data |
10 tests | GLM-4.5 Air speed / latency N/A / N/A input / output No data | GLM-5 speed / latency 41 tok/s / 18111ms input / output No data |
10 tests | GLM-4.5 Air speed / latency 63 tok/s / 18555ms input / output No data | GLM-5 speed / latency 36 tok/s / 24627ms input / output No data |
GLM-4.5 Air glm-4.5-air speed / latency No data input / output $0.014/M/$0.075/M | GLM-5 glm-5 speed / latency No data input / output $0.068/M | |
GLM-4.5 Air z-ai/glm-4.5-air:free speed / latency No data input / output $0.010/request | GLM-5 glm-5 speed / latency No data input / output $0.010/request | |
GLM-4.5 Air zai-org/GLM-4.5-Air speed / latency No data input / output $0.025/M/$0.140/M | GLM-5 glm-5 speed / latency No data input / output $95.45/M |
Weighted outcome: GLM-5. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Output
| Features | Text inputText outputTool callingReasoning | Text inputText outputTool callingStructured outputsJSON modeReasoning |
|---|
