Tagged: ai-benchmarks

12 articles

Latest

OpenAI's GPT-6 Astra scores 98% on FrontierMath Tier 4, ships to Plus users

Meta's Muse Spark 1.3 hits 62 on intelligence index at $0.55 per task

Google ships Gemini 3.8 Flash: 73.7% on DeepSWE, but 'working harder' burns tokens

Anthropic's Claude Fable 5.1 doubles science benchmark scores and slashes cache costs 75%

AI Aces Connections But Still Can't Rotate a 3D Object in Its Head

AI models can't beat 70 handcrafted puzzle games humans solved 100%

Artificial Analysis launches Optima to benchmark AI on your data, not theirs

Grok 4.6 lands in Cursor with 500K context and a $6 output price

Intelligence nets $7.9M for Design Arena, a 5.3M-user feedback engine already pulling $60M ARR

Claude Opus 5 beats Fable 5 on benchmarks but hallucinates 50% of the time

Industrial AI's Blind Spot: Why 'Lone Wolf' Agents Fail 150 Real-World Tests

Forget Memorization: FutureBench Tests If AI Can Actually Predict Tomorrow