readable AI benchmarks (simplified)
Z AI
GLM-5.3 (Max)
GLM-5.3 (Max) has a Quality Score of 63.0, ranking 47th among 571 scored models. Per 1M tokens, pricing is $1.40 input, $4.40 output, and $0.260 cached input. It accepts text input, outputs text, and has a 1M token context window. Its Reliability Score is 57.1, ranking 81st among 573 scored models, above average (total average: 36.5). Its Value Score is 44.6, high compared with the total Value average of 31.4.
Model specification
- Reasoning
- reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $1.40
- Output
- $4.40
- Cached Input
- $0.260
- Cache write
- not available
- Cost per task
- $2.01
Capability
- Intelligence
- 44.8
- Coding
- not available
- Agentic
- not available
- Omniscience
- 14.3
- Correct
- 33.9%
- Blended price
- $0.902
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 53.4%
Artificial Analysis benchmarks
- GDPval-AA v2
- 58%
- τ³-Banking
- 50%
- SciCode
- 59%
- Humanity’s Last Exam
- 42%
- GPQA Diamond
- 92%
- CritPt
- 19%
- AA-Omniscience
- 57%
- AA-LCR
- 80%
DeepSWE operational cross-check
- Pass@1
- 69.0%
- Avg steps/scored attempt
- 124.47
- Mean cost/scored attempt (USD)
- $3.99
- Mean output tokens/scored attempt
- 80,435.61
- Mean duration/scored attempt (s)
- 2116 s
Mean cost/scored attempt is the official feed's mean_cost_usd: mean benchmark cost in USD per scored attempt under the source's cost basis. It is not Artificial Analysis cost per task and not token price (USD per 1M tokens). Mean output tokens/scored attempt is mean_output_tokens, also averaged over every scored attempt including scored failures. Mean duration/scored attempt is mean_duration_seconds; it is informational only, and wall-clock varies with provider and host load. These three fields do not affect Quality Score, Value Score, or Reliability. Epoch General ECI's benchmark basket includes DeepSWE v1.1, so Epoch General ECI and this DeepSWE cross-check are not independent evidence.
Similar models
- GLM 5.3 FlashZ AIQuality Score 59.0Value Score 53.0
- GLM-5.2 (Max)Z AIQuality Score 52.0Value Score 36.9
- GLM-5.3 (Low)Z AIQuality Score 49.3Value Score 34.9
- GLM-5 (Reasoning)Z AIQuality Score 46.5Value Score 34.2
- GLM-5.1 (Reasoning)Z AIQuality Score 45.3Value Score 32.3
- GLM-5-TurboZ AIQuality Score 41.4Value Score not available