The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **HLE w/ tools**: We use sampling parameters of `temperature=1.0` and `top_p=0.95` for evaluation, with a maximum generation length of `163,840` tokens. The evaluation is conducted with a maximum context length of `300,000` tokens, using a context management strategy. We use GPT-5.6-luna (medium) as the judge model.
条件
GLM-5.3; exact HLE task release, effort, endpoint and precision not stated. 2026-11-18按完整模型卡修正单位、指标/题集或协议标注,数字不变。
GLM-5.3 · HLE w/ Tools · GLM-5.3模型卡;w/ Tools; full/text-only subset not stated · Scores and configurations
GLM-5.3 record for HLE w/ Tools · GLM-5.3模型卡;w/ Tools; full/text-only subset not stated. 1 score record for this release, including 1 exact value (may include historical records). Includes 2 source locations.
The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **HLE w/ tools**: We use sampling parameters of `temperature=1.0` and `top_p=0.95` for evaluation, with a maximum generation length of `163,840` tokens. The evaluation is conducted with a maximum context length of `300,000` tokens, using a context management strategy. We use GPT-5.6-luna (medium) as the judge model.
Conditions
GLM-5.3; exact HLE task release, effort, endpoint and precision not stated. 2026-11-18按完整模型卡修正单位、指标/题集或协议标注,数字不变。