A focused feed of models, agents, research and open-source releases for people building with AI.
Artificial Analysis updated its six domain Capability Indexes to v2.0, aligning them with Intelligence Index v5 . Every index now weights Non-Hallucination and Agentic Tool Use more heavily, reflecting real deployment risks.
Artificial Analysis is exposing the CritPt v2 physics benchmark grading server through its API. CritPt covers 71 composite research challenges built by 50+ active physics researchers across 30+ institutions.
Prime Intellect audited AutomationBench, OfficeQA Pro v2, and HLE-Diamond, finding broken graders and reward hacks that distort reported model scores. AutomationBench fixes replaced prose request bodies with JSON Schemas; Opus 5.5 hit 92.15% partial, 70.83% strict.
Ai2 released StateBench , a benchmark splitting state tracking into four algebraic complexity tiers. Frontier models including GPT-6 Sol, Claude Opus 5.5, and Gemini 3.8 Flash drop to 13% or lower on hardest problems.
MER-Bench introduces Meme Reappraisal: flipping a meme's emotion while keeping scene, characters, and layout intact. Task inspired by cognitive reappraisal in psychology, framed as constrained multimodal generation.
Snorkel AI released RIFT , a framework that audits rubrics using nine named failure modes. RIFT identifies injected rubric defects with 75% accuracy versus 56.7% for an LLM judge baseline. Applied to 147 tasks across five public benchmarks in finance, medicine, coding, advice, and reasoning.
OpenAI unveiled LifeVal , a benchmark grading models on everyday personal-assistant tasks. Built from surveys of around 4,000 ChatGPT users plus 100 detailed task authors. Covers childcare, finances, government services, meal planning, apartment hunting, and caregiving.
Parallel open-sourced PWS-Decisions , 300 classification questions whose answers depend on live web facts. Parallel Decisions API scored 76.22% vs Perplexity 50.89%, OpenAI 41.67%, Jev 33.44%. OpenAI Decisions scored 2.2x lower on PWS-Decisions than on static JevBench, exposing a live-web gap.
AA-AgentPerf adds Throughput per $/hr , a value-for-money metric for inference systems. Pricing comes from Silicon Data daily rental indices for H100, H200, B200 and B300. NVIDIA B300 leads overall; B200 matches it at faster output speeds on some models.
AA-Omniscience v1.1 shrinks to 3,000 questions across 6 domains, removing saturated and ambiguous items. Gemini 4 Carbon leads with Net Score 54, ahead of Claude Opus 5.5 (48) and Claude Fable 5.1 (46). Rank order holds with 0.98 Spearman correlation to v1, but median Net Score drops 0.6 points.
Gemini 4 Carbon (High) debuts #1 Text, #2 Agent, #4 WebDev on Arena. Carbon costs $1.80 per task, 72% cheaper than Claude Opus 5.5 at the top. GPT-6.1 Terra (Max) hits Agent Arena #8 at just $0.62 median cost per task. MAI-Image-2.7-Preview jumps to #3 in Single Image Edit, +45 pts over v2.6.
Utopai X now supports image-to-video and ranks #2 on AA-Video-I2V v2.1 , behind Dreamina Seedance 2.5. Only model in the top 2 on both AA-Video-T2V v2.1 and AA-Video-I2V v2.1. Post-trained on MiniMax H3; beats base H3 (768p), Hyperflow H3, and MiniMax H3 Max on I2V.
Artificial Analysis launched an independent HLE-Diamond leaderboard as part of Intelligence Index v5. HLE-Diamond is a cleaned 1,000-question subset of Humanity's Last Exam from CAIS and Scale AI. Gemini 4 Carbon leads at 69.1%, Claude Opus 5.5 max at 67.9%, GPT-6 Astra max around 64%.
Gemini 4 Carbon scores 40% at $4.04/task on FrontierCode 2.0 , near state of the art. Gemini 4 Argon trails at 26.3% and costs more at $6.41 per task. Claude Opus 5.5 leads the benchmark at 45.5%, showing it remains far from saturated.
Parallel launched Parallel for Finance , a universal index upgrade applied across all its APIs with no new subscription. On FinSearchComp T3, Parallel Advanced hits 57.4% accuracy at up to 2x lower cost than Exa and Perplexity.
CATT benchmark fine-tunes Qwen3.5-4B on fictitious facts for unambiguous attribution ground truth: project page . Redundancy and lexical distractors consistently break gradient-based attribution; TRAK falls to zero recall with distractors.
Jev and winnow:e4b matched the reference on all 12 Claude Code fixes, Claude in a plain message matched 9, and a filename rule matched 3. Only one of the 12 fixes left a bug behind, and all four pickers caught it, so the test measures fit and says nothing yet about catching more bugs.
Artificial Analysis launched the Progress Index v1 , a single capability scale for every LLM since 2022. Uses item response theory to compare models tested on different benchmarks over time. Frontier rose ~68 points in 2025 and 56 so far in 2026, roughly double 2023's pace.
Phonic 1 (High) debuts at #1 on the Speech to Speech Index at 87.1, edging out Grok Voice 3.0. Leads τ-Voice agentic benchmark at 79.9%, a 5.4 point gap over GPT-Live-1 (Astra, medium). Scores 98.9% on Big Bench Audio reasoning, third behind StepAudio 3 and Qwen Audio 3.0.
A tiny U-Net learns to turn chest vibrations into 12-lead ECG waveforms, with a dataset that finally includes precordial lead positions.
A new framework turns physics-based expert models into interpretable fit scores, beating random forests on seismic monitoring when training data is scarce.
Exa added 3.2 million podcast episodes with full transcripts to its search API, letting agents query 2.2 million hours of audio for free.
Artificial Analysis just rolled out AA-Video-I2V v2.1, a 1080p image-to-video benchmark with 58,000+ blind human votes across 10 use cases and 10 capabilities.
GitHub's new runtime orchestration layer routes between Claude and GPT models, scoring near Opus 5.5 at half the cost per task.
No stories match these filters.
