Artificial Analysis
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications
Artificial Analysis launches AA-PersonalityBench: 36 models, 30 traits, 900 questions
A new benchmark measures not answer correctness but how LLMs communicate: 30 traits, 8 indices and 21 formatting metrics. It tests 36 models, from Claude to GPT-6.
Artificial Analysis launches HealthBench: GPT-6 Astra leads with 66.0%
Artificial Analysis has launched HealthBench and HealthBench Professional leaderboards. GPT-6 Astra scores 66.0% on the clinician set, while Claude Sonnet 5.5 leads the general test with 62.1%.
Reflection releases Beam: 501B parameters and 30 points on the Intelligence Index
Reflection's first model is the second-best American open-weights model: 30 points on the Artificial Analysis Intelligence Index, using half the tokens of K2 Horizon.
NVIDIA RTX Spark N1X Runs a Local Qwen3.8 27B Agent in 18.7 Minutes
A Surface Laptop Ultra with the N1X chip and 128 GB of memory ran the AA-AgentPerf-Local agent workload in 18.7 minutes, twice as fast as a MacBook Pro with M5 Pro.
Vera Rubin NVL72 beats GB300 by up to 5.7x in tokens per megawatt in AA-AgentPerf
Artificial Analysis published the first Vera Rubin NVL72 results in its agentic coding benchmark: up to 5.7x throughput per megawatt over GB300 and a record 906 tok/s per user.
NVIDIA releases Nemotron 3.5 Super: 26 AA points and 630 tokens/s
Nemotron 3.5 Super VL doubles its predecessor's Intelligence Index score and becomes the best American open-weight model. The compact Bolt 74B-A9B launched alongside it.
AA-Robotics v0.1: GPT-6 Astra controls a robot arm and scores 69 out of 100
Artificial Analysis launched AA-Robotics v0.1, where LLMs control a 6-axis arm. Leader GPT-6 Astra scored 69.4, but it needs 30 minutes and $16.36 per task.
Artificial Analysis launches Decision Index: Jev 1.13 leads with 58 points
Artificial Analysis launched a benchmark for decision models that pick an answer in a single call. Jev 1.13 scored 58 at $42 per million tasks, ahead of GLiDE and Microsoft.
Meta releases Muse Wonder and Wonder Full: intelligence index rises from 48 to 56
Muse Wonder and Muse Wonder Full score 52 and 56 on the Artificial Analysis Intelligence Index, up from 48 for Muse Spark 1.3. Agentic benchmarks gained most, and so did the price.
Artificial Analysis launches AA-3D: Claude Sonnet 5.5 leads with 1194 Elo
A new benchmark asks agents to build an interactive 3D scene in three.js. Claude Sonnet 5.5 takes first place (1194 Elo), but the top four are statistically indistinguishable.
FrontierCode: Top AI Models Fail Maintainer Review in 42% of Attempts
Cognition and Artificial Analysis launched FrontierCode 1.1: Claude Opus 5.5 leads with 52% and a 58% pass rate, at $10.15 per task. GPT-6.1 Sol scores 49% for $0.81.
GPT-6 Sol Daybreak Blue Tops Cyber Index: +32 Points and $1.77 per Task
Artificial Analysis added reduced-restriction models to its Cyber Index. The closed GPT-6 Sol Daybreak Blue took the lead, scoring 32 points above the public version.
Harvey LAB-AA v1.1: Grok 4.7 Leads With 9.4% After Hallucination Check
Artificial Analysis and Harvey added a hallucination check to their legal benchmark: Grok 4.7 scores 9.4%, while two-thirds of Muse Spark 1.3's passing tasks contain errors.
Anthropic releases Claude Haiku 5.5: 43 points on the AA index and a price of $0.10 per million tokens
Claude Haiku 5.5 scores 43 on the Artificial Analysis Intelligence Index, drops to $0.10/$0.50 per million tokens and gets 1M context, but uses three times the tokens of GPT-6 Luna.