Unverified50% confidenceFactExact time
Jason Wei's 2022 paper demonstrated that giving 8 examples in the prompt enabled a 540-billion-parameter model to reach the then-best level on the GSM8K math word problem benchmark.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
14 Core Concepts of Reasoning Models: From Chain of Thought to GRPO Explained
youtubeBrix AI10/29/2026
Related Entities
Related Claims
UnverifiedAfter models approached perfect scores on GSM8K, researchers immediately needed to introduce harder benchmarks, giving rise to the phenomenon of benchmark saturation.70% similarUnverifiedWithout changing the prompt, the capabilities of the SymCE-trained model transfer to mainstream mathematical reasoning benchmarks such as GSM8K, MATH-500, and MMLU-college-math.69% similarUnverifiedCommon reasoning benchmarks include GSM8K (elementary school math word problems), MATH (competition-level math problems), StrategyQA (multi-hop commonsense reasoning), and others; these benchmarks require multi-step derivation and have automatically verifiable answers.68% similarUnverifiedThere is a qualitative gap between the currently popular evaluation benchmarks GSM8K and MATH and frontier research-level mathematical reasoning67% similarUnverified随着模型参数规模从亿级扩展到千亿级，LLM展现出涌现能力，包括多步推理、类比迁移和不确定性表达67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1116031API
curl https://kongchang.com/api/v1/knowledge/claims/1116031MCP
get_claim(id=1116031)