Unverified50% confidenceBenchmarkExact time
On the code generation task HumanEval, 8-bit scored 92.7%, significantly higher than OQ4E's 89.6%.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn the math reasoning task GSM8K, OQ4E answered 954 questions correctly (95.4%), while 8-bit only answered 924 correctly (92.4%), with the 4-bit version coming out 3 percentage points higher.75% similarUnverifiedIn the MMLU Pro test, 8-bit narrowly beat OQ4E with 60.6% versus 59.9%.63% similarUnverifiedIn the MMLU test, OQ4E surpassed 8-bit with 84.5% versus 82.8%.63% similarUnverifiedV4 Pro Max满血推理模式下算法竞赛3206分、编程93.5分、科学问答90.1分、软件工程80.6分、终端操作67.9分61% similarUnverifiedo3在Codeforces的评分达到2727，超越99.95%的人类参赛者59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/907288API
curl https://kongchang.com/api/v1/knowledge/claims/907288MCP
get_claim(id=907288)