Epoch AI estimates that open-weight cyber capabilities are about 6–7 months behind the closed frontier. Zai’s GLM-5.3 is the highest-scoring open-weight model on its Cyber ECI, scoring 160 and beating OpenAI’s GPT-5.4, released in March. https://t.co/F0D6nSnM69
UBTECH introduces Thinker-WM, a multimodal world model that jointly models RGB video, depth, and robot actions through a shared Unified Dynamics Transformer. In material supplied by UBTECH and republished by QbitAI, the company reports leading results on WorldOlympiad, EWMBench, and WorldArena1.0 Track-1, including scores of 0.740 on WorldOlympiad and 4.66 on EWMBench. The model supports six capability modes through shared weights, and adding depth improved RoboTwin single-task success by 15 percentage points over a baseline without depth.
With our latest update, it is now easier than ever to create and run custom benchmarks in Optima. This allows you to evaluate models on evals tailored to your use cases With Optima you can: ➤ Go from idea to personalized benchmark in 3 steps ➤ Compare model intelligence, https://t.co/xQ4U35CCml
The Verge’s three reviewers spent a week testing five Nvidia RTX Spark laptops, finding capable graphics and generally workable Windows on Arm apps alongside high prices, weaker CPU performance than Apple rivals, and demanding local AI workloads. Sean Hollister’s Asus ProArt P16 lasted roughly 5 hours to 5 hours and 40 minutes during everyday work. Their local AI experiments encountered substantial battery drain, heat, slow responses, and uneven results, despite configurations offering up to 128GB of unified memory.
Why it matters: The hands-on comparisons show how large unified memory and capable graphics translate into everyday tradeoffs in local AI workloads, battery life, and software compatibility.
Google DeepMind’s Gemini 4 Argon scored 97.5 percent on ARC-AGI-3 using the Provider Adapter Harness at a cost of $4,800, behind GPT-6 Astra’s 99.9 percent. Its score fell to 49.8 percent at low reasoning in the Standard Harness, where API problems prevented completion of all games. Epoch AI placed Argon at 165 ECI points, close to Opus 5.5 and GPT-6 Astra, although early estimates ranked it eighth in math and sixth in software engineering.
Why it matters: The comparison shows how testing environments can change benchmark standings, providing context for interpreting Argon’s proximity to leading models alongside its weaker math and software engineering results.
Aravind Srinivas says Gemini 4 Argon has set a new SoTA on the Wide-And-Deep-Research (WANDR) benchmark and is now available to all Perplexity users in fast search and Computer (agent) modes. https://t.co/0U671BhbMj The quoted @perplexity_ai announcement specifies availability for Pro and Max subscribers. https://t.co/n1TyI9RhBX
Why it matters: The post identifies availability across fast search and Computer modes, while its broader access claim differs from the quoted announcement limiting availability to Pro and Max subscribers.
MAI is the most accurate & most popular transcription model on OpenRouter across all languages and use cases. Try it out for your agents now! 👇 https://t.co/rHOlsQWzro
Jev reached 35% of paid teams within two weeks of launch, the fastest adoption recorded by Vercel and nearly twice the reach of Sonnet 5.5. Typesafe AI’s lightweight decision model selects among predetermined outputs for cheaper, faster classification. The figures come from Vercel’s AI gateway, which may undercount providers with their own APIs; open-source models now represent more than 70% of gateway tokens and nearly 25% of spending.
Reflection’s first model, Beam, scores 30 on the Artificial Analysis Intelligence Index, placing it #2 among US open weights models. Beam is an open weights model with 501B total and 23B active parameters, released on Hugging Face.
Liquid AI has released d1-ultra, which Artificial Analysis reports leads its Decision Index v1.0 with a score of 65. On AA-Omniscience-Decision, its non-hallucination rate rose to 85% from d1’s 2%, while accuracy fell to 32% from 41%. This non-hallucination metric measures how often the model says it does not know among questions it does not answer correctly. d1-ultra takes 92 ms per task and costs $0.042 per 1M input tokens, billed only on input tokens.
Turns out le Chonk is into rocket science. Mistral Large 4 scoring well in engineering and astronomy on Ulam’s private benchmark, STEMBench: https://t.co/OW3reppzWN https://t.co/3BbnbEuYvP
Artificial Analysis reports that NVIDIA's Vera Rubin NVL72 delivers up to ~5.7x GB300 NVL72's throughput per megawatt on DeepSeek V4 Pro in initial AA-AgentPerf results. Its advantage is largest at faster per-user speeds; peak-throughput gains range from 1.14x to 1.45x across the four tested models. NVIDIA submitted all Vera Rubin results using TensorRT-LLM and vLLM with NVIDIA Dynamo; the benchmark replays real agentic coding sessions and measures throughput per megawatt of measured GPU power alongside per-agent output speed.
Meta has released Muse Spark Open, an 816B (42B active) open-weights model that Artificial Analysis reports scores 39 on its Intelligence Index, making it the #1 US open-weights model. Muse Spark Open (xhigh) scores 22 points above Muse Glimmer (high, 17), Meta's 30B dense open-weights model. https://t.co/jf31mQNINe
Why it matters: The comparison places Muse Spark Open 22 points above Muse Glimmer on the same intelligence index, providing a concrete reference for the reported capability gap between Meta's open-weights models.
We’re proud to share that Meta Omnilingual Automatic Speech Recognition (ASR) has been named one of @TIME’s Best Inventions of 2026! Meta Omnilingual ASR is a suite of models providing ASR capabilities for over 1,600 languages, including 500 low-coverage languages never before https://t.co/pQjBPvE5XG
NVIDIA's RTX Spark N1X puts up to 128 GB of unified memory and a Blackwell GPU in a Windows laptop. In Artificial Analysis's first AA-AgentPerf-Local results, an RTX Spark laptop completes its local agent workload on Qwen3.8 27B in 18.7 minutes. Artificial Analysis describes RTX Spark's N1X chip as essentially the GB10, linking to https://t.co/520A4lOOdB
We are hosting our first "Bench Summit" to bring together people excited about pushing the frontier of benchmarking, model evals, and more. Great benchmarks are a gating function for model progress, lots to do here! Join us in SF: https://t.co/7qqyPLe5Vp
Argon has a similar performance profile on ARC-AGI-3 as Astra, François Chollet says, adding that Google is back at the frontier. https://t.co/a6GGEsMN4A The quoted ARC Prize post reports Gemini 4 Argon’s verified ARC-AGI-3 results of 97.5%, $4.8K with a provider adapter harness and 49.8%, $5.8K with the standard harness, plus 91.3%, $0.32/task on ARC-AGI-2 and 98.5%, $0.16/task on ARC-AGI-1. https://t.co/8siwgfBJcr
Why it matters: The reported ARC-AGI-3 scores distinguish provider adapter and standard harness results, providing context for Chollet’s comparison of Argon with Astra and his assessment of Google’s frontier position.
Nvidia’s Nemotron 3.5 Super VL is now the leading US open weight model, scoring 26 on the Artificial Analysis Intelligence Index. Artificial Analysis reports twice the intelligence of its predecessor, Nemotron 3 Super (13), using ~60% fewer output tokens per task. https://t.co/VMIiXLcLDj
GPT-6-Astra, running in OpenAI's Codex environment without human hints, solved 49 of 50 TheoPhysEval problems across eleven theoretical physics subfields, costing just under $116 overall. Anthropic's Opus 5.5 scored 92 percent, while both models reached 92 percent without internet access. The researchers emphasize that the benchmark tests calculations using known methods, while choosing promising research questions remains a separate challenge for current agents.
Why it matters: The benchmark distinguishes proficiency in concrete physics calculations from the ability to choose fruitful research questions, clarifying which parts of scientific work its high scores actually measure.
Gemini 4 Argon scores 165 on the Epoch Capabilities Index (ECI), on par with Fable 5.1 (165) but behind Opus 5.5 (167) and GPT-6 Astra (166). While behind the ECI frontier, Argon is the closest Google has come since Gemini 3.1 Pro in Feb, and a big jump from Gemini 3.8 Flash (157). https://t.co/PvZvD4KyvI
Artificial Analysis asked AI models to build the Eiffel Tower in 3D offline. Claude Opus 5.5 and Grok 4.7 included all 72 inscribed scientists’, engineers’, and mathematicians’ names in the correct order, although the shared brief never mentioned them. Claude Opus 5.5 also matched each set to its orientation in Paris. Both models worked as agents without internet access, and the names first appeared in their generated code, never in files or tool outputs they read.
Thoughtful review of Muse Wonder and Muse Wonder Full from the lovely @clairevo! https://t.co/VneEUPK6f6
Welcome to the era of embodied AI. We are launching AA-Robotics v0.1, our research preview that measures frontier language model performance on understanding, planning, and acting in the physical world. In v0.1, each model is given control of a 6-axis robot arm (5 joints and a https://t.co/fCwpnDlvB2
Six months ago, frontier AI models could barely beat Slay the Spire. Now, according to our new SpireClimb benchmark, they win 90%+ of runs at the easiest difficulty, and up to 20% of runs at the hardest. https://t.co/KvV5gD2RBh
Google engineer Haydn Belfield says Google DeepMind has seen no measurable AI-driven acceleration of AI research despite substantial automation. AI writes more than 75 percent of production code, but every change receives human review before submission; Argon completes about half of RE-Bench's 74 ML engineering tasks. Google's General Capability Index shows steady Gemini capability growth without statistically significant acceleration, contrasting with researchers' warnings of a possible intelligence explosion.
muse wonder full is SOTA on VCB 1-100, new coding eval out today https://t.co/PdN1m05g1V
Artificial Analysis is adding AMD MI355X results to AA-AgentPerf, which replays real coding agent sessions with prompt caching and tool-call delays. On a single 8-GPU node, MI355X delivers ~15% to 40% more throughput per MW than B200 on DeepSeek V4 Pro 0813 between 35 and 75 tok/s per user. DeepSeek V4.1 Flash matches NVIDIA Blackwell performance for a single agent but trails as load rises; GLM-5.2/5.3 and Kimi K3 also trail the compared NVIDIA systems. Results use ROCm nightly and dev builds of vLLM and SGLang; Kimi K3 comparisons use NVIDIA multi-node configurations.
Artificial Analysis evaluated SpaceXAI’s Grok Voice 3.0 using the Rex voice through the SpaceXAI Realtime API, reporting a #1 Speech to Speech Index score of 86.9, up from Grok Voice 2.0 at 81.3. It ranked #3 in arena preference and #1 in task success rate at 94.8%. Average time to first audio on Big Bench Audio was 0.81 seconds versus 0.70s for Grok Voice 2.0, while input audio pricing remained $4.80 per hour.
@itsnoahd says Muse Wonder (not full) comes in 4th on Noahbench, just below Opus 5.5, and calls its price-to-performance-to-speed ratio “perfect.” They say each task takes 10 minutes. Alexandr Wang calls it “a chic entry into noahbench.” https://t.co/VLAlRoBsDN
Artificial Analysis added DeepSeek V4.1 Flash to AA-AgentPerf, its benchmark replaying real agentic coding sessions with prompt caching and tool-call delays. At 100 tokens/s per user, GB300 leads with approximately 261M tokens/s per MW, followed by B300 at approximately 220M and MI355X at approximately 128M. Compared with DeepSeek V4 Pro 0813, V4.1 Flash scores 39 versus 36 on the Artificial Analysis Intelligence Index and delivers approximately 1.3x to 6.2x the throughput per MW at that user output speed, depending on hardware.
Try Muse Wonder Full on your hardest coding tasks—it will surprise you! “By my vibe testing, It's better than Astra. Not quite as good as Claude Code Fable and 5.5 Opus.” https://t.co/8RTGZ434kG
@Hesamation is benchmarking models on Stronghold Crusader, a strategic game they grew up with. They said Muse Wonder playing the game on an old laptop is “ridiculously fun to watch,” and that they have tested Opus, Sol, GLM flash, Kimi K3, and more models. Alexandr Wang reacted: “cmon muse wonder i believe in you invest in your tech treeeeeeee” https://t.co/dSUEmGVxV7
@lightseekorg reports 685 output tokens/s per user for Qwen3.8-Flash-Next. Congrats to @lightseekorg on the impressive TokenSpeed results! 🚀 Great to see Qwen3.8-Flash-Next reaching 685 output tokens/s per user on Nvida GPUs. Excited to see the community unlock more of Qwen’s inference potential!
In Claude Code, Sonnet 5.5 scores 68 on the Coding Agent Index at max effort and 63 at xhigh. The xhigh setting costs $3.33 per task versus $14.19 at max, a 77% reduction for 5.5 fewer Index points. Max generates 4.8× as many output tokens and takes 3.4× as many turns, while improving all three benchmark scores; its largest gain is on Terminal-Bench 4.0, from 58.1% to 66.2%.
Muse Wonder Full on Merge’s Intelligence Index.
Artificial Analysis now publishes cache hit rates for tracked model endpoints and provider-level Cost per Task for open weights models. Cache hit rates are measured using multi-turn agentic coding tasks; provider cost comparisons use the same token counts from each model's Intelligence Index run. GLM-5.3 (max) costs vary ~9x, from $0.92 on Makora to $8.68 on Nebius, largely because of input pricing despite both having high cache hit rates. Across 21 providers (25 endpoints), cache hit rates range from 41% to 100%.
Victoria Song finds the camera-free Ray-Ban Meta Audio glasses comfortable and useful as open-ear headphones, while finding Muse Spark helpful mainly for simple requests and reminders. Her review unit lasted two full workdays without returning to its case, but audio suffered from sound leakage and loud surroundings. Removing the camera eased her discomfort wearing smart glasses in public, though she argues that it does not resolve broader privacy concerns and finds the glasses expensive for their current capabilities.
Artificial Analysis reports that Fish Audio’s Drama 3 Preview ranks #1 among open-weights models on all three of its Text to Speech leaderboards and leads all models in Pronunciation Robustness. It scores 93.2% on pronunciation robustness, ahead of Eleven v4 at 91.7% and Eleven v4 Turbo at 90.1%, while ranking #10 in Provider Voice and #14 in Controlled Voice. Its weights are available on Hugging Face under the Fish Audio Community License, and Fish Audio API pricing is $15/1M characters.
Why it matters: The comparison separates pronunciation robustness from voice preference rankings, showing how Drama 3 Preview’s lead on one measure differs from its placement on others.
Artificial Analysis reports that Gemini 4 Argon is now GA, matching GPT-6 Astra on its Intelligence Index at 60% of the Cost per Task under discounted pricing until November 30. Argon costs $1.99 per task and $2/$10 per 1M input/output tokens, rising to $4/$20 after November 30, with a 95% cache-read discount. Artificial Analysis also reports substantial agentic evaluation improvements and a 15% hallucination rate on AA-Omniscience, the lowest among models scoring 45+ on its Intelligence Index.
Why it matters: The comparison separates intelligence scores from task costs, showing how Argon's temporary pricing affects its cost advantage over GPT-6 Astra at a comparable intelligence level.
@PawelHuryn reports that Muse Wonder Full 1.0 scored 44 on a test of 105 bugs across 2 repos, ranking behind GPT-6 Astra (45) and ahead of Fable 5.1 (43), and calls it a match for Anthropic and OpenAI. Alexandr Wang says Muse Wonder is “crushing” bug fixing.
