glm-5.1 - GAIA
GAIA score 42.5 from M&M
View sourceZ.ai
Z.ai's flagship reasoning and coding model family for long-horizon agentic workflows.
55.9
Quality Score
---
Arena ELO
Undisclosed
Parameters
203K
Context
Sign in to join the discussion
140.2K
Downloads
1.7K
Likes
Apr 2026
Released
Benchmarks
3
API
1
General
3
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
GAIA score 42.5 from M&M
View sourceNavigation Guide How to Switch Models Guides API Reference Scenario Example Coding Plan Released Notes Terms and Policy Help Center GLM Coding Plan Overview Usage Policy FAQ Legacy Plan Migration Notice Guide Quick Start Coding Tool Helper Tool Integration How to Switch Models MCP Integration Learning Resources Best Practice Memory-mechanism Campaign Rules Invite Friends, Get Credits On this page Switching Models in Claude Code Step 0 Claude Code default configuration Step 1
Z.ai published benchmark or leaderboard evidence for GLM-5.1, GLM 5.1.
View sourceGLM-5.1 is now available through Ollama Cloud. 198K context window listed. GLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin.
View sourceAs 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.
View sourceAs 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-wise KV Cache storage scheme. Instead of duplicating all layers on every GPU, https://t.co/OGptVovbtf
GLM-5.1 is now available through Ollama Cloud. 198K context window listed. GLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin.
Navigation Guide How to Switch Models Guides API Reference Scenario Example Coding Plan Released Notes Terms and Policy Help Center GLM Coding Plan Overview Usage Policy FAQ Legacy Plan Migration Notice Guide Quick Start Coding Tool Helper Tool Integration How to Switch Models MCP Integration Learning Resources Best Practice Memory-mechanism Campaign Rules Invite Friends, Get Credits On this page Switching Models in Claude Code Step 0 Claude Code default configuration Step 1
Z.ai published benchmark or leaderboard evidence for GLM-5.1, GLM 5.1.