Unverified50% confidenceBenchmarkExact time
Evaluated with llama.cpp on a Tesla T4, the MMLU subset retention rate is 92.9% (344/502).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/30/2026
First Seen
Valid until: 1/28/2027
Sources
Related Entities
Related Claims
UnverifiedEvaluated with llama.cpp on a Tesla T4, the HumanEval pass@1 retention rate is 96.7% (29/30).72% similarUnverifiedModels like GPT-4 and Claude 3.5 surpassed 90% accuracy on MMLU, significantly diminishing its discriminative power66% similarUnverifiedMMEA achieves an accuracy of 96.48% on the DynToM benchmark.64% similarUnverifiedWhen paired with GPT-4o, FinDialogLens achieves 94.3% accuracy on trade outcome determination.62% similarUnverifiedLlama 3.1 405B's score on MMLU is already close to the level of GPT-4o, and Qwen 2.5 72B has surpassed GPT-4 Turbo on certain metrics in math and code generation benchmarks.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1115187API
curl https://kongchang.com/api/v1/knowledge/claims/1115187MCP
get_claim(id=1115187)