winbuzzer.com/2026/03/24/g...
GPT-5.4 Pro Cracks Open Math Problem, Epoch AI Confirms
#AI #OpenAI #LLMs #Mathematics #GPT54Pro #GPT54 #AIModels #Science #Frontiermath
1
0
0
0
Hashtag
#Frontiermath
Advertisement · 728 × 90
Когда нейросеть решит то, что не решил никто? В середине 2024 года GPT-4 спотыкался на школьных задачах, а к концу...
#FrontierMath #Epoch #AI #LLM #бенчмарки #открытые #задачи #GPT-5 #Gemini #теория #чисел
Origin | Interest | Match
0
0
0
0
A Zenodo analytics screenshot showing 191 total downloads. The text identifies 191 as a Sophie Germain Prime and the post marks the project's expansion beyond octonions into 32-dimensional math space and beyond with Applied Pathological Mathematics.
191 downloads. A Sophie Germain Prime (2p + 1 = 383). We are inspired by the French mathematician and dare to venture with her perseverance beyond octonions with Applied Pathological Mathematics.
doi.org/10.5281/zeno...
#SophieGermain #Sedenions #FrontierMath #MathSky #SciSky #AIResearch #DeepTech
3
1
0
0
A Zenodo analytics screenshot showing 191 total downloads. The text identifies 191 as a Sophie Germain Prime and the post marks the project's expansion beyond octonions into 256-dimensional with Applied Pathological Mathematics.
191 downloads. A Sophie Germain Prime (2p + 1 = 383). We are inspired by the French mathematician and dare to venture with her perseverance beyond octonions with Applied Pathological Mathematics.
doi.org/10.5281/zeno...
#SophieGermain #Sedenions #FrontierMath #MathSky #SciSky #AIResearch #DeepTech
1
1
0
0
New math benchmark from math.science-bench.ai :
209 research-level mathematics problems from Combinatorics, Algebra, Geometry, Number Theory, and others.
👉 math.science-bench.ai/benchmarks/
#AI #Mathematics #AIBenchmark #EpochAI #FrontierMath #OpenAI #Gemini #Grok
8
3
0
0
The first ScienceBench benchmark is live!
👉 math.science-bench.ai/benchmarks/
We tested all major AI models on 100 research-level mathematics problems.
#AI #Mathematics #AIBenchmark #EpochAI #FrontierMath #OpenAI #DeepSeek
1
0
0
0
Benchmarking for #LLM models is becoming increasingly complex and controversial, as seen in the #FrontierMath controversy. Companies in the development of benchmarks raises concerns about #fairness & #transparency, reinforcing the point that model performance needs to be validated by the community.
0
0
0
0
OpenAI's o3 model faces controversy after claims of early access to FrontierMath test questions, leading to accusations of unfair advantages and manipulation.
#AI #OpenAI #LLM #Agent #FrontierMath
aidisruptionpub.com/p/openai-o3-...
2
0
0
0
How embarrassing! I have to take back that I submitted or have seem problems from #FrontierMath.
I just reveived an email from Humanity's Last Exam, a similar database, not restricted to mathematics, and realized that I contributed to that dataset instead!
#math #MathSky #LLM #AI
2
0
1
1
#FrontierMath is the hardest math data set for LLM testing.
Seeing that #OpenAI #o3 can solve 25% -- after all other models two months ago were at ~2% -- is just incredible.
I submitted some problems and looked at others. No mathematician can get even close to 25%, I guess.
#MathSky #LLM #AI #ML
8
1
2
2
OpenAIのo3モデルが数学の超難問データセット「FrontierMath」で25.2％のスコアを獲得した衝撃を数学者が語る #Gigazine (Dec 25)
#数学AI #大規模言語モデル #AI研究 #推論モデル #FrontierMath
0
0
0
0
Sind #KI-Systeme automatisch Mathe-Genies? Fehlanzeige! ❌ Neue, superharte Aufgaben legen die Schwächen von #KI-Modellen offen. #Mathematik bleibt also vorerst noch eine menschliche Domäne.
Die Matheaufgabensammlung und die Versuchen kommen #FrontierMath (epoch.ai/frontiermath)
2
0
1
0
Today's Top AI Went Up Against Expert Mathematicians. It Lost Badly.
Today's Top AI Went Up Against Expert Mathematicians. It Lost Badly.
https://buff.ly/411Rdnw
#FrontierMath #ArtificialIntelligence #Mathematics
0
0
0
0
La organización de investigación Epoch AI lanzó #FrontierMath , un nuevo punto de referencia matemático que ha llamado la atención en el mundo de la #IA porque contiene cientos de problemas de nivel experto que los principales modelos de IA resuelven menos del 2 % de las veces. tinyurl.com/2dbxl4xr
0
0
0
0