Expired60% confidenceFactExact time
Top autoregressive models such as GPT-4o and Claude 3.5 have already exceeded 95% accuracy on GSM8K, leading to benchmark saturation.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/17/2026
First Seen
Valid until: 10/15/2026(expired)
Sources
Related Claims
UnverifiedGPT-5.4 was reversed by a "trusted source" on 44.7% of questions, Grok-4.20 had a reversal rate as high as 87.5%, while Gemini-3.1-Pro was nearly unaffected at just 0.6%.77% similarUnverifiedModels such as GPT-4, Claude, and Gemini successively broke the 90% accuracy threshold on MMLU, causing the benchmark to lose its discriminative power.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/543860API
curl https://kongchang.com/api/v1/knowledge/claims/543860MCP
get_claim(id=543860)