Un x2 sur les benchmark qui testent l'AGI, c'était jamais arrivé. Là c'est beaucoup d'un coup
RESEARCH
-
Grok 4 evaluation results on ARC-AGI benchmark
By
–
Info chula sobre la evaluación de Grok 4 en ARC-AGI
-

Tencent’s ArtifactsBench: Automated Evaluation for LLM Visual Artifacts
By
–
Tencent's Hunyuan team introduced ArtifactsBench, an automated evaluation pipeline for LLM-generated visual artifacts It assesses models on 1,825 diverse tasks with MLLM-as-Judge evaluating visual artifacts, achieving 94.4% ranking consistency with human experts
-
Ai2 Launches FlexOlmo: Decentralized Language Model Co-Development
By
–
Ai2 dropped FlexOlmo, a new paradigm for the co-development of language models
— The Rundown AI (@TheRundownAI) 10 juillet 2025
It allows each data owner to locally branch from a shared public model, add an expert trained on their data locally, and contribute this expert back to the shared modelpic.twitter.com/xiaaBKKOTSAi2 dropped FlexOlmo, a new paradigm for the co-development of language models It allows each data owner to locally branch from a shared public model, add an expert trained on their data locally, and contribute this expert back to the shared model
-

Grok 4 Benchmarks Outperform O3, Gemini 2.5 Pro, Claude Opus 4
By
–

XAI GROK 4 BENCHMARKS: OpenAI O3 is smoked
Gemini 2.5 Pro is smoked
Claude Opus 4 is smoked IT'S OVER, GROK 4 HAS WON. -
Grok 4 Analysis: Hidden CoT, Web Search Integration
By
–
A few quick observations on Grok 4:
1) Hidden CoT with very little information in the reasoning trace
2) Uses web search a lot (not just searching X)
3) Have not seen it use code to run calculations or solve non-coding problems yet, generally less aggressive about tools than o3 -
Grok 4 Scores 50.5% on HLE Benchmark, Score Still Rising
By
–
Pour l’AGI, c’est le HLE qui compte avant tout c'est un peu la mesure de l'AGI. Et d’après ce qu’on m’a dit, le score n’est même pas encore stabilisé ! Le dernier benchmark HLE passé par GROK 4 affiche 50,5 %. Plus ils le laissent tourner, plus le score augmente. On ne connaît
-

Grok 4 Achieves Perfect AIME 2025 Score and Doubles ARC-AGI Performance
By
–


Alors là… pour l'instant GROK 4 sur le papier, grosse percée ! Sur le benchmark AIME 2025 il a fini le Game (100% de score). Premier modelé à réussir. Sur l'ARC-AGI, un x2 par rapport à ce qu'il se fait aujourd'hui. Et surtout sur le HLE (humanity last exam), il fait
-
Company AI API Lacks Transparency After Model Incident
By
–
Hard to imagine a lot of excitement inside companies for using the API at this stage, given the lack of transparency – I am surprised they didn't take advantage of all the eyeballs to offer some sort of post mortem on yesterday. They pulled their own model down as a result.
-
AIKosh Workshop July 2025: India’s Unified AI Dataset Platform
By
–
Mark Your Calendars! The upcoming AIKosh Workshop is set to take place on July 25, 2025! Join the IndiaAI Mission in exploring how your organisation can contribute to and benefit from AIKosh — India’s unified platform for trusted, India-specific AI datasets. What to