New video w/ some extreme logic tests on the new GPT-4.5 by OPENai.
Compare GPT-4.5 (the most expensive AI model) to DeepSeek R1 (open-source) and check the causal reasoning performance of the new SONNET 3.7 to the new GROK 3.
Note that GPT-4.5 is a non-reasoning model. Sonnet 3.7 - I test the non-extended-thinking model on logic (not on pure coding).
I compare the reasoning results with the aider benchmarks for pure coding.
#logicalreasoning
#tests
#airesearch
Compare GPT-4.5 (the most expensive AI model) to DeepSeek R1 (open-source) and check the causal reasoning performance of the new SONNET 3.7 to the new GROK 3.
Note that GPT-4.5 is a non-reasoning model. Sonnet 3.7 - I test the non-extended-thinking model on logic (not on pure coding).
I compare the reasoning results with the aider benchmarks for pure coding.
#logicalreasoning
#tests
#airesearch
- Category
- Artificial Intelligence
- Tags
- artificial intelligence, AI models, LLM
Post your comment
Up Next
Autoplay
-
25:42
Open AI SHIPS: "GPT o1" First Look! ("Strawberry" Chain of Thought Reasoning)
-
11:03
New Claude 3.7 Sonnet Just CRUSHED Every AI Model In The World! (First HYBRID REASONING Model Ever)
-
12:06
New Claude 3.5 Sonnet is Better Than GPT-4o
-
01:02
Two AI agents play game OVER SOUND: Sonnet 3.7 vs GPT 4.5
-
08:33
Claude 3.7 Sonnet AGENTS: FULLY FREE Way to Create YOUR CUSTOM AI Agents with 3.7 SONNET in SECONDS!
-
41:21
AI and the future of humanity | Yuval Noah Harari at the Frontiers Forum
-
13:10
Can AI really save the World? ft. Bill Gates
-
Asking Sophia, Hanson Robotic’s human-like AI robot, to show her range of emotions.
-
01:00
Man WRONGFULLY Arrested Using AI #shorts
-
00:20
Robot Attacks Factory Worker! #shorts
Comments