Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
BenchmarksZ.ai5d ago
GLM-5.2 - Overview - Z.AI DEVELOPER DOCUMENT
Navigation Language Models GLM-5.2 Guides API Reference Coding Plan Released Notes Terms and Policy Help Center Get Started Quick Start Overview Pricing Core Parameters SDKs Guide Migrate to GLM-5.2 Language Models GLM-5.2 HOT GLM-5.1 GLM-5 GLM-5-Turbo GLM-4.7 GLM-4.6 GLM-4.5 GLM-4-32B-0414-128K Vision Language Models GLM-5V-Turbo GLM-4.6V GLM-OCR AutoGLM-Phone-Multilingual GLM-4.5V Image Generation Models GLM-Image CogView-4 Video Generation Models CogVideoX-3 Vidu Q1 Vidu 2
Navigation Language Models GLM-4.7 Guides API Reference Coding Plan Released Notes Terms and Policy Help Center Get Started Quick Start Overview Pricing Core Parameters SDKs Guide Migrate to GLM-5.2 Language Models GLM-5.2 HOT GLM-5.1 GLM-5 GLM-5-Turbo GLM-4.7 GLM-4.6 GLM-4.5 GLM-4-32B-0414-128K Vision Language Models GLM-5V-Turbo GLM-4.6V GLM-OCR AutoGLM-Phone-Multilingual GLM-4.5V Image Generation Models GLM-Image CogView-4 Video Generation Models CogVideoX-3 Vidu Q1 Vidu 2
As models, contexts, and workloads grow, hidden assumptions in inference infrastructure can surface as output anomalies. Reliability requires more than throughput, latency, and availability. It also r
As models, contexts, and workloads grow, hidden assumptions in inference infrastructure can surface as output anomalies. Reliability requires more than throughput, latency, and availability. It also requires preserving the correctness of model state behind every generation.
After fixing correctness issues, we turned to the next bottleneck: Prefill throughput and GPU memory pressure in long-context Coding Agent serving. To address this, we introduced LayerSplit, a layer-w
After fixing correctness issues, we turned to the next bottleneck: Prefill throughput and GPU memory pressure in long-context Coding Agent serving. To address this, we introduced LayerSplit, a layer-wise KV Cache storage scheme. Instead of duplicating all layers on every GPU, https://t.co/OGptVovbtf
Usage limits tripled for GLM-5-Turbo in GLM Coding Plan! Enjoy the same high-volume capacity as GLM-4.7 during non-peak hours. Availability: Anytime except 2–6 AM ET. Ends: April 30.
Retrieval-augmented QA pipelines often route retrieved passages through an LLM rewriter before a smaller reader, lifting F1 by tens of points on multi-hop benchmarks; this gain is typically credited to improved evidence quality. We ask whether that lift is causally driven by the gold answer string appearing in the rewritten context rather than by curation per se, using a controlled intervention audit. For each rewritten context we re-run the reader after one of four controlled edits to the compile output: removing the gold answer span, replacing a length-matched random non-answer span (placebo), or injecting the gold into rewrites where it was absent (at the prefix or at a midpoint sentence boundary). Across twelve completed (cell, baseline) intervention runs spanning three reader families (Qwen2.5-7B, Qwen3.5-35B, GLM-4.7), two datasets (HotpotQA, 2WikiMultihopQA), and three compiler arrangements (MA-only, MB-only, MA+verify), removing the gold answer drops reader F1 by 28 to 64 points beyond the length-matched placebo on paired answer-in-compile strata, and prepending the gold into rewrites that lacked it raises F1 by +0.7 to +9.7 points in 10 of 12 (cell, baseline) combinations. A companion five-sentinel audit shows the conventional single-[MASK] probe is itself sentinel-fragile: on 2Wiki it reports a +4.12~F1 ``non-leakage residual'' that flips to -3.33 to -7.81~F1 under four alternative sentinels and fails an equivalence test for three of those four (1/4~pass). We do not propose a new rewriter or mitigation; we release the intervention runner and the sentinel panel so that other rewriter-gain claims can be tested against the same standard.
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
INT2 KV-cache quantization is attractive for long-context LLM serving, but it remains difficult to make both accurate and deployable. Simple rotations such as Hadamard transforms reduce outliers, but still degrade at INT2 because they are not aligned with downstream attention. We propose OSCAR, an Ultra-low-bit KV Cache quantization method that estimates attention-aware covariance structures offline and uses them to derive fixed rotations and clipping thresholds for quantization. In this way, it aligns KV quantization with the covariance structures that attention actually consumes. More importantly, we not only provide theoretical justification but also develop a fully deployable OSCAR system with a custom INT2 attention kernel that remains compatible with paged KV-cache serving and fused kernel pipelines, enabling seamless integration into modern LLM serving frameworks such as SGLang and vLLM.
We evaluate our methods on recent reasoning models with reasoning traces of up to 32k tokens across 5 tasks. On Qwen3-4B-Thinking-2507 and Qwen3-8B, OSCAR reduces the BF16 accuracy gap to 3.78 and 1.42 points, respectively, while naive rotation INT2 collapses to nearly zero. We further scale OSCAR to Qwen3-32B and GLM-4.7 (358B params), where it remains effectively on par with BF16. On long context - RULER-NIAH up to 128K, OSCAR remains robust on both Qwen3 models, while naive rotation INT2 collapses. System-wise, OSCAR reduces KV-cache memory by approximately 8x, improves throughput by up to 7x at large batch sizes under the same memory budget, and accelerates batch-size-1 decoding by up to 3x over BF16 due to reduced memory bandwidth overhead.
Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
We study parallel test-time scaling for long-horizon agentic tasks such as agentic search and deep research, where multiple rollouts are generated in parallel and aggregated into a final response. While such scaling has proven effective for chain-of-thought reasoning, agentic tasks pose unique challenges: trajectories are long, multi-turn, and tool-augmented, and outputs are often open-ended. Aggregating only final answers discards rich information from trajectories, while concatenating all trajectories exceeds the model's context window. To address this, we propose AggAgent, an aggregation agent that treats parallel trajectories as an environment. We equip it with lightweight tools to inspect candidate solutions and search across trajectories, enabling it to navigate and synthesize information on demand. Across six benchmarks and three model families (GLM-4.7, Qwen3.5, MiniMax-M2.5), AggAgent outperforms all existing aggregation methods-by up to 5.3% absolute on average and 10.3% on two deep research tasks-while adding minimal overhead, as the aggregation cost remains bounded by a single agentic rollout. Our findings establish agentic aggregation as an effective and cost-efficient approach to parallel test-time scaling.
Navigation Language Models GLM-5.2 Guides API Reference Coding Plan Released Notes Terms and Policy Help Center Get Started Quick Start Overview Pricing Core Parameters SDKs Guide Migrate to GLM-5.2 Language Models GLM-5.2 HOT GLM-5.1 GLM-5 GLM-5-Turbo GLM-4.7 GLM-4.6 GLM-4.5 GLM-4-32B-0414-128K Vision Language Models GLM-5V-Turbo GLM-4.6V GLM-OCR AutoGLM-Phone-Multilingual GLM-4.5V Image Generation Models GLM-Image CogView-4 Video Generation Models CogVideoX-3 Vidu Q1 Vidu 2
Navigation Language Models GLM-4.7 Guides API Reference Coding Plan Released Notes Terms and Policy Help Center Get Started Quick Start Overview Pricing Core Parameters SDKs Guide Migrate to GLM-5.2 Language Models GLM-5.2 HOT GLM-5.1 GLM-5 GLM-5-Turbo GLM-4.7 GLM-4.6 GLM-4.5 GLM-4-32B-0414-128K Vision Language Models GLM-5V-Turbo GLM-4.6V GLM-OCR AutoGLM-Phone-Multilingual GLM-4.5V Image Generation Models GLM-Image CogView-4 Video Generation Models CogVideoX-3 Vidu Q1 Vidu 2
