readable AI benchmarks (simplified)
Z AI
GLM-4.6 (Non-reasoning)
GLM-4.6 (Non-reasoning) has a Quality Score of 28.6, ranking 263rd among 551 scored models. Per 1M tokens, pricing is $0.575 input, $2.20 output, and $0.355 cached input. It accepts text input, outputs text, and has a 200k token context window. Its Reliability Score is 34.2, ranking 268th among 553 scored models, below average (total average: 35.6). Its Value Score is 21.3, low compared with the total Value average of 30.7.
Quality Score28.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score21.3
Factual reliability34.2
Cache Discount38%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 200k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.575
- Output
- $2.20
- Cached Input
- $0.355
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 14.9
- Coding
- not available
- Agentic
- not available
- Omniscience
- -31.7
- Correct
- 21.4%
- Blended price
- $0.584
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 74.5%
Correct 21.4%Incorrect 53.1%Partial / not attempted 25.5%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 5%
- GPQA Diamond
- 63%
- CritPt
- 0%
- AA-Omniscience
- 34%
- AA-LCR
- 26%
Similar models
- GLM-4.7 (Non-reasoning)Z AIQuality Score 26.5Value Score 20.0
- GLM-4.6V (Non-reasoning)Z AIQuality Score 22.0Value Score 17.9
- GLM-5 (Non-reasoning)Z AIQuality Score 38.8Value Score 28.6
- GLM-5.1 (Non-reasoning)Z AIQuality Score 38.0Value Score 27.0
- GLM-4.7-Flash (Non-reasoning)Z AIQuality Score 15.9Value Score 14.5
- GLM-5.2 (Non-reasoning)Z AIQuality Score 40.6Value Score 28.8