Reasoning protocol: temperature=1.0; top_p=0.95; maximum generation length=163,840 tokens; AIME/HMMT/IMOAnswerBench use the card's prescribed answer-format system prompt; GPT-5.5 (medium) judge. Metric and unit are not stated.
条件
GLM-5.2目标列;Reasoning protocol: temperature=1.0; top_p=0.95; maximum generation length=163,840 tokens; AIME/HMMT/IMOAnswerBench use the card's prescribed answer-format system prompt; GPT-5.5 (medium) judge. Metric and unit are not stated.
GLM-5.2 · IMOAnswerBench · GLM-5.2模型卡;unknown · Scores and configurations
GLM-5.2 record for IMOAnswerBench · GLM-5.2模型卡;unknown. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Reasoning protocol: temperature=1.0; top_p=0.95; maximum generation length=163,840 tokens; AIME/HMMT/IMOAnswerBench use the card's prescribed answer-format system prompt; GPT-5.5 (medium) judge. Metric and unit are not stated.
Conditions
GLM-5.2目标列;Reasoning protocol: temperature=1.0; top_p=0.95; maximum generation length=163,840 tokens; AIME/HMMT/IMOAnswerBench use the card's prescribed answer-format system prompt; GPT-5.5 (medium) judge. Metric and unit are not stated.