Unverified50% confidenceBenchmarkExact time
The final version of DeepSeek R1 and the December 2024 version of OpenAI o1 trade wins on benchmarks: 79.8% vs 79.2% on AIME 2024, 97.3% vs 96.4% on Math500, with o1 slightly ahead on Codeforces.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/30/2026
First Seen
Valid until: 11/13/2026
Sources
14 Core Concepts of Reasoning Models: From Chain of Thought to GRPO Explained
youtubeBrix AI10/29/2026
Related Entities
Related Claims
UnverifiedOn the 2024 AIME math exam, OpenAI o1 averaged 70%, scored 74% on a single attempt, and reached 83% after 64-sample voting, while GPT-4o scored only 12%.71% similarUnverifiedOllama分发的DeepSeek R1各版本均经过GGUF格式量化处理（通常为Q4_K_M或Q8_0精度），将每个参数从16位浮点数压缩至4-8位，显存占用减少50%-75%，推理质量损失通常在5%以内64% similarUnverifiedDeepSeek V4.1 claims to achieve 74 on SWE, but the blogger found that this was the best result cherry-picked from multiple tests, with open code testing at 65 and PI testing at 66.62% similarUnverifiedIn the Codeforces rating, o1's score is far lower than that of o3-mini-high.62% similarUnverifiedOpen-source models scored lower: Qwen3 235B scored 11/12, both sizes of Gemma 4 scored 9/12, DeepSeek R1 scored 7/12, and GLM-5 scored 5/12.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1116038API
curl https://kongchang.com/api/v1/knowledge/claims/1116038MCP
get_claim(id=1116038)