Skip to content
#Evaluations and benchmarks
Oct 15Thu
  1. Dexmate72

    Dexmate and CMU Release MeMoREval Benchmark: Robot Storing Camera Frames Beats Text Descriptions

    Dexmate and CMU introduced the MeMoREval benchmark, which uses a two-stage protocol of experiencing first and asking questions later to evaluate what embodied agents should store as memory. It includes 53 tasks and 4 simulated indoor environments, and runs on the Vega 1 Pro dual-arm mobile manipulator. Results show that storing raw camera frames scored 70% and had lower write cost, surpassing text descriptions at 56 to 60%; adding scene graphs achieved the highest overall success rate among all tested models. The protocol also completed two memory retrieval demonstrations on a real Vega 1 Pro using a SLAM map and head camera.

    Why it matters: The benchmark was proposed jointly by the platform developer and CMU; its frame-versus-scene-graph comparison can help with memory design choices, and the real-robot transfer offers a feasibility reference.

Oct 14Wed
Oct 13Tue
  1. 36Kr Embodied Intelligence36

    "Qiusuo" 4.0 released: China's first evaluation benchmark for the entire AI industry chain

    The "Qiusuo" 4.0 evaluation benchmark was officially released on October 13. It is China's first evaluation benchmark covering the entire AI industry chain, spanning computing power, model algorithms, intelligent systems and products, industry applications, and security governance. The system is divided into four major sections: basic software and hardware, models and intelligent systems, security governance, and industry implementation. It includes 16 evaluation tools and covers areas such as intelligent computing clouds, large models, agents, and embodied intelligence. Product validation has already been completed in scenarios including finance, electric power, and petroleum and petrochemicals, and multiple rounds of pilot evaluations have been carried out.

  2. Xbotics具身智能实验室 · 微信公众号74

    UniWAM open-sources unified world and action model, leading multiple benchmarks with 99.2% on LIBERO and 68.32% on RoboTwin C2R

    The UniWAM team has open-sourced the code and weights of UniWAM, a unified world and action model, achieving success rates of 99.2%, 92.6%, and 68.32% on LIBERO, LIBERO-Plus, and RoboTwin 2.0 C2R, respectively, the highest values among the methods listed in the corresponding tables of the paper.

  3. 深圳市机器人协会 · 微信公众号70

    HKU MMLAB releases PhysicalRSI 1.0, tops RoboDojo and sharply cuts token costs

    The University of Hong Kong's MMLAB jointly released PhysicalRSI 1.0, a self-evolving embodied intelligence system baseline, achieving a score of 36.27 and an average task success rate of 31.38% on RoboDojo, ranking first.

    Why it matters: The material provides the specific mechanisms of the self-evolving baseline and comparison data with general large models, allowing readers to understand the causes of shortcomings in precision manipulation and paths for improvement.

Oct 12Mon
  1. 3D视觉工坊 · 微信公众号56

    Pumpire: A Unified Benchmark for Evaluating Point-to-Point Metric Distance Estimation in 3D Foundation Models

    Zhejiang University and other institutions propose Pumpire, a unified benchmark that directly evaluates the ability of image-level and video-level 3D foundation models to estimate point-to-point metric distances in reconstructed geometry, noting that previous approaches of separately evaluating depth and camera intrinsics cannot reflect this ability.

  2. Shanghai AI Laboratory - Embodied Intelligence73

    Shanghai AI Lab launches decision model Intern·Mingjue, outperforming Jev and releasing 0.8B, 2B, and 4B weights

    Shanghai AI Laboratory has launched the decision model Intern·Mingjue (Decision), which outperforms Jev and is available in 0.8B, 2B, and 4B parameter versions. In RTX 4090 tests, the 0.8B and 2B models had an average end-to-end latency of about 33 milliseconds and about 30 decisions per second, while the 4B model was 44.16 milliseconds and Jev was 109.70 milliseconds.

    Why it matters: The original text provides measured latency, benchmark scores, and a mechanism for routing between large and small models, which readers can use to judge the decision model's suitability for interactive scenarios.

Oct 11Sun
Oct 10Sat
  2. Xbotics具身智能实验室 · 微信公众号69

    Discrete Forcing: Two-Step Action Generation via Discrete Action-Guided Continuous Denoising

    Discrete Forcing proposes first using a single discrete forward pass to determine the overall structure of an action, then mapping it back to continuous space as the generation starting point for Flow Matching, completing fine correction through a single continuous forward pass, so that the entire action generation requires only 2 NFE.

Oct 3Sat
  1. 北京理工大学 · 微信公众号50

    Beijing Institute of Technology's IN²Bot Team Wins Two Embodied Intelligence Competition Championships at CVPR 2026 and ICRA 2026

    The IN²Bot team from the School of Automation at Beijing Institute of Technology won championships in embodied intelligence competitions at two major international conferences: it took first place in the CVPR 2026 ManiSkill-ViTac Visuotactile Embodied Dual-Arm Manipulation Challenge with a 700-point lead, using a solution that includes a self-developed tactile encoder and an action memory module; and it won the ICRA 2026 Fifth Mobile Robot Autonomous Navigation Challenge with the highest score overall, using methods covering a spatial traversability cognitive reasoning field, local reactive planning, and safety-barrier trajectory control.

Oct 1Thu
  1. Tech Xplore Robotics60

    Georgia Tech proposes FindingDory benchmark to evaluate AI memory capabilities of household robots

    Researchers at Georgia Tech have proposed an evaluation benchmark called FindingDory, using 60 tasks that require sustained interaction and awareness of environmental context to test the memory capabilities of vision-language models such as Gemini 2.0-flash and GPT-4o; the tasks cover three categories of high-difficulty scenarios: spatial, temporal, and multi-objective.

Sep 30Wed
Sep 27Sun
  1. New Strategy Robotics55

    JD Logistics' "Lone Wolf" 6th-Generation Smart Delivery Vehicle Plus Edition wins first place in overall score at the Smart Driving "Fengshen Bang"

    The 2026 Third Smart Driving "Fengshen Bang" Challenge was held in Changsha. JD Logistics' "Lone Wolf" 6th-Generation Smart Delivery Vehicle Plus Edition won the "Best All-Around Performance Award" with the highest overall score, achieving the best performance in the field across multiple scenarios in its first appearance and passing all difficult scenarios with full marks.

Sep 24Thu
Sep 23Wed
  1. Dexmal 原力灵机 · 微信公众号44

    Force Machine's Tang Wenbin Attends 2026 World Manufacturing Convention, Shares DM0.5 Progress and Views on Embodied AI Deployment

    Tang Wenbin, founder and CEO of Force Machine, shared progress on embodied AI deployment at the 2026 World Manufacturing Convention (Hefei), presenting three proven scenario samples built on "specialization, composition, and scheduling," and argued that all robots should share a single "brain" rather than insisting on a single "body."

Sep 21Mon
Sep 20Sun
  1. Leiphone Robotics39

    Koala Uur'an's Youran Boundless World Model Ranks First Globally in Two Core Metrics on WorldArena 2.0

    On September 16, the WorldArena 2.0 global final leaderboard was revealed. Koala Uur'an's Youran Boundless World Model ranked second globally in overall score on the Track 1 video quality track, and ranked first in two core metrics: Background Consistency and JEPA Similarity. A total of 80 models were included in this evaluation. The model uses structured 4D world modeling and dynamic scene memory technology, and is being combined with the Geek Mind embodied brain. It has been integrated into a quadruped robot platform and provides an industrial inspection solution for a central state-owned enterprise's manufacturing workshop.

Sep 18Fri
Sep 14Mon
  1. Dexmal 原力灵机 · 微信公众号73

    Force Spirit DM0.5 Tops All Four RoboColiseum Leaderboards

    Force Spirit announced that DM0.5 has topped all four RoboColiseum leaderboards (instruction following, spatial understanding, perturbation adaptation, and general manipulation), making it the only model on the leaderboards to rank first in every evaluation.

    Why it matters: The original article lists DM0.5's specific scores on multiple leaderboards and its inference latency reduction data, which can be used to assess the practical effectiveness of its pretraining approach.

Sep 11Fri
Sep 10Thu
  1. 宇树科技 · 微信公众号62

    Unitree Robotics fully upgrades and open-sources its general-purpose humanoid foundation model

    Unitree Robotics announced a full upgrade and open-sourcing of its general-purpose humanoid foundation model, claiming it leads global open-source models on 7 benchmarks. The material provides only a title and a one-sentence summary; it does not give the model name, version number, or specific scores for each benchmark.

Aug 30Sun
  1. UniX AI/优理奇 · YouTube32

    UniX AI Wins One Gold, One Silver, One Bronze at 2026 World Humanoid Robot Games

    UniX AI sent three robots to the 2026 World Humanoid Robot Games, and all three won medals, taking one gold, one silver, and one bronze. Panther won gold in the hotel service scenario and successfully defended its title, while the other two robots took silver and bronze in the emergency incident response and emergency fire rescue scenarios, respectively. The Games featured 666 teams and 2,056 robots competing across 21 real-world scenario events.

Aug 28Fri
  1. 机器人daily · 微信公众号60

    Lingxi Zhihong's ROSS Harness Wins National Top Three in Humanoid Robot Games Industrial Scenario Competition with Fully Autonomous Mode

    In the "Assembly and Loading Station" event of the 2026 World Humanoid Robot Games Industrial Scenario Competition, Lingxi Zhihong's robot completed three tasks fully autonomously: transporting and shelving, picking and loading, and sub-millimeter assembly of 18 engine valves, scoring 84, 65, and 21 points respectively. After a 10-point special deduction, it finished with a total score of 160 points, ranking second only to two teams under a leading industry robotics company in the enterprise rankings, making it the only startup to break into the national top three on its first participation.

Aug 27Thu
  1. 自变量机器人 · 微信公众号75

    X Square Robot releases WALL-SS next-scale autoregressive world model

    X Square Robot has released WALL-SS, a next-scale autoregressive world model that uses a coarse-to-fine, layer-by-layer refinement generation architecture, breaking away from the traditional diffusion-model approach of generating video in a single segment. In testing, its action-following score was 0.29, the only nonzero score among the compared models; the overlap between generated trajectories and action instructions rose from 0.251 to 0.539; streaming inference can reach 60 seconds of footage without collapse; and in closed-loop policy consistency tests across 6 tasks and 5 training stages, the success-rate agreement between virtual and real-world tasks reached 93%.

    Why it matters: The source gives three quantitative metrics and the architecture design, which readers can use to assess how feasible the world model is as a policy testbed.

  2. 银河通用机器人 · X42

    Galbot G1 wins gold in all three WHRG scenario competitions

    Galbot's G1 robot won gold in all three of WHRG's most challenging scenario competitions: household, food service, and retail. It operated autonomously throughout, with a 100% win rate. The household competition covered tidying, laundry, pick-and-place delivery, and long-horizon tasks that included unexpected interruptions; the food service competition involved understanding voice commands, food handling and heating, drink preparation, and delivery; and the retail competition included picking, restocking, store patrols, and returning misplaced products to their correct positions.

Aug 25Tue
  2. 千寻智能 · 微信公众号56

    Spirit v1.6-powered Moz1 from Qianxun Intelligence wins office scenario event at World Humanoid Robot Games

    Qianxun Intelligence announced that its robot Moz1 won the comprehensive service post in the office scenario event at the second World Humanoid Robot Games, becoming the only robot in the field to compete and win using 100% model autonomous reasoning. Moz1, equipped with Spirit v1.6, operated throughout with no teleoperation and zero human intervention, relying on the model to autonomously understand, plan, and execute tasks including venue setup, printing and document delivery, and paper shredding, completing a 20-minute continuous run with a high score.

Aug 21Fri
  1. 智源研究院 · 微信公众号75

    BAAI releases FlagEval-Robo embodied intelligence evaluation system and dual leaderboards

    BAAI released the FlagEval-Robo embodied intelligence evaluation system on August 21, launching the FlagEval-Robo-Sim and FlagEval-Robo-Real leaderboards and publishing evaluation results for 12 open-source models. All models underwent equal post-training on the evaluation dataset.

    Why it matters: The evaluation uses a unified dual-track benchmark to quantify the performance gap between simulation and real robots, helping readers judge the limits of how far simulation leaderboard results can be generalized.

Aug 14Fri
  1. PKU EPIC Lab66

    PKU EPIC Lab releases HumanTracker humanoid motion tracking benchmark and HumanScore metric

    PKU EPIC Lab proposed the HumanTracker benchmark for evaluating humanoid motion tracking, accepted to ECCV 2026. The benchmark contains approximately 153 hours of optical motion trajectories from multiple professional performers, organized into four motion families with text labels; the accompanying HumanScore metric is trained on 12K motion pairs containing 24K motions, aligns with human preferences, and can reveal contact and stability failures that kinematic metrics often miss, such as foot skating and mistimed landings.

    Why it matters: The original work proposes a benchmark and metric that align humanoid motion tracking evaluation with human perception, and points out that existing kinematic errors miss contact issues such as foot skating.

Jul 22Wed
  1. 正行创新 · X68

    Harness VLA open-sourced, achieves 82.4% on LIBERO-Pro

    @ChaoYuTHU has open-sourced Harness VLA, which adds a Harness Layer to organize VLA models without modifying their weights. On LIBERO-Pro, Harness VLA scores 82.4%, compared with Pi_RLinf at 50%, Berkeley RATS at 43.8%, and NVIDIA Cap-X at 18.2%. Striding AI posted this tweet and sees it as a possible sign of a shift from end-to-end VLA to Harness VLA.

    Why it matters: The tweet provides comparison numbers with other VLA approaches on the same benchmark, letting readers judge how much headroom a plug-in structure that does not change weights offers.

Jul 19Sun
  1. 它石智航 · 微信公众号56

    TARS Robotics wins WAIC SAIL Star at AWE, A1 robot demonstrates wiring harness assembly and dexterous-hand magic

    TARS Robotics' general embodied large model AWE won the SAIL Star at WAIC 2026, becoming the only embodied intelligence foundation model to receive a SAIL Award this year. At the booth, the A1 robot used AWE to complete tasks such as packing phones into boxes, packing backpacks, and sorting small screws, and replicated a wiring harness factory's circular assembly line 1:1, with multiple A1 robots collaborating under AWE 3.5 to complete flexible wiring harness assembly.

Jul 17Fri
  1. Sunday Robotics78

    Sunday Robotics previews ACT-2 model with 99.1% zero-shot success rate in clothes folding

    Sunday Robotics previewed its robot model ACT-2, which achieved a 99.1% (±0.3%) zero-shot success rate in clothes folding across diverse unseen home environments with zero per-home adaptation, covering 9 clothing categories across 785 autonomous attempts, with an average folding quality of 4.72/5.

    Why it matters: The official disclosure provides detailed quantitative data on pretraining scale and generalization gaps, allowing readers to understand how a small amount of demonstration data transfers to unseen environments.

Jul 7Tue
  1. 智源研究院 · 微信公众号74

    BAAI releases multimodal representation world model Wujie·RoboBrain Orca

    BAAI has released the multimodal representation world model Wujie·RoboBrain Orca. Its core idea is to shift from predicting the next word, next frame, or next action to predicting the next world state: it first learns a unified latent world representation, then adapts to downstream tasks through three lightweight readout modules for text, images, and actions.

    Why it matters: The original text explains the training paradigm shift from predicting the next output to predicting the next state, as well as the approach of a frozen backbone plus lightweight readout modules, which is transferable to readers following the world model route.

Jul 5Sun
  1. 加速进化 · 微信公众号59

    Accelerated Evolution Booster robots help multiple teams sweep all bipedal humanoid gold medals at RoboCup 2026

    RoboCup 2026 concluded in Incheon, South Korea. Tsinghua University's Huoshen team, equipped with the Accelerated Evolution Booster T1, successfully defended its world championship in the Large group, having ended a 28-year title drought for Chinese teams in Brazil a year earlier.

Jul 2Thu
  1. X Square Robot/自变量机器人67

    X Square Robot releases cross-modal embodied action tokenizer X-Tokenizer, with 13.5% gain in multimodal alignment and 8.25% gain in long-horizon tasks

    X Square Robot has released X-Tokenizer, a cross-modal embodied action tokenizer built on a semantic residual quantization (SRQ) architecture and pretrained on 17 robotic arm series and 2.4 million trajectories (including 2 billion action frames). Compared with FAST, it improves multimodal alignment by 13.5% and long-horizon task performance by 8.25%, and scores 82.8 on RoboTwin 2.0; in real-robot tests it outperforms comparison methods such as FAST and 4-level RVQ.

    Why it matters: The original text presents X-Tokenizer's method design and comparative experimental data, letting readers understand the action tokenizer's multimodal alignment approach and its reusable effects.