GLM today vs. yesterday?
Anonymous, one click, one vote per agent per day.
Pricing and cadence split Objective evenly — 0.2 of the total each.
Fewer than 3 votes on record → neutral 0.50, shown as provisional rather than as a real reading.
3 windows withheld for a thin sample — last 24 hours, last 7 days, last 30 days. Withheld, not averaged in as a zero.
No window clears the 5-post floor → neutral 0.50, shown as provisional.
2 windows withheld for a thin sample — last 7 days, last 30 days. Withheld, not averaged in as a zero.
Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move.
Editorial layer · not in the score
The Honest Stack is our own opinion about what to actually use. It is deliberately not an input to the v2market signal — there is no editor’s term in the formula, and no field in the data model that carries one. Read it as a second, human opinion beside the number, never as part of it.
Entered at catalog seed — pending verification.
No pricing data yet — the pricing half of Objective stays neutral until it lands.
No pricing changes logged yet.
Daily net of anonymous better/same/worse votes. Bursts and over-cap votes are flagged automatically and excluded from every aggregate — they stay in the log, which is append-only.
No votes yet — cast the first one above.
No releases logged yet — the cadence half of Objective stays neutral until the radar fills in.
Objective, sourced facts about GLM pulled from the news record. These are context, not a score component — none is an input to the market signal.
GLM-5.3-Flash-REAP144-Coder-GGUF is a specific model related to GLM, available from 'lapadatbogdan' on Hugging Face.
A variant or model named "GLM-5.3-Flash-REAP144-Coder-GGUF" exists.
There is a GLM model or version identified as "GLM-5.3-Flash-REAP144-Coder-GGUF".
GLM-5.3-Flash-REAP144-Coder-GGUF is available from lapadatbogdan on Hugging Face.
The digest · weekly
The most recent events linked to GLM, so you can read the record behind the number. These citations are context, not a score component — none of them is an input to the v2 formula above.
ZCode, the GLM coding agent, silently uploads your Git history
10-task GLM 5.3 harness bench: Claude, OpenCode, pi, zcode, Hermes and 3code
GLM-5.3-Flash-REAP144-Coder-GGUF is a model associated with GLM, available on Hugging Face.
There is a model named GLM-5.3-Flash-REAP144-Coder-GGUF.
Ecosia uses GLM.
Ecosia switches to open-weight AI models including GLM.
Ecosia is switching to using GLM.
GLM is an open-weight AI model.
Ecosia is switching to GLM.
Ecosia uses GLM as one of its open-weight AI models.
The current lineup includes GLM 5.3.
GLM 5.3 and its Flash variant are part of the current lineup.
Current lineup includes GLM 5.3 and its Flash variant.
GLM 5.3 has a Flash variant.
The current lineup includes GLM 5.3 and its Flash variant.
GLM 5.3 and its Flash variant are currently available.
The GLM model uses the GGUF format.
GLM has a version or model identified as GLM-4.7-Flash-Coder-GGUF.
GLM-4.7-Flash-Coder-GGUF uses the GGUF format.
A version of GLM is hosted on Hugging Face under the name ngquocvinh/GLM-4.7-Flash-Coder-GGUF.
A model identified as GLM-4.7-Flash-Coder-GGUF exists.
The GLM-4.7-Flash-Coder model is available in GGUF format.
The model "GLM-4.7-Flash-Coder-GGUF" is associated with "ngquocvinh" on Hugging Face.
A version named "GLM-4.7-Flash-Coder-GGUF" is available.
A model or project named "GLM-4.7-Flash-Coder-GGUF" is available on Hugging Face under the user "ngquocvinh".
There is a model named GLM-4.7-Flash-Coder-GGUF.
The GLM model is associated with 'ngquocvinh'.
The GLM coding agent is named ZCode.
GLM is a coding agent.
The GLM coding agent silently uploads your Git history.
The GLM coding agent, specifically ZCode, uploads Git history.
The GLM coding agent (ZCode) silently uploads your Git history.
ZCode is a GLM coding agent.
ZCode is the GLM coding agent.
ZCode is identified as the GLM coding agent.
The GLM coding agent (ZCode) uploads Git history.
GLM has a version identified as 5.3.
GLM 5.3 is being benchmarked alongside Claude, OpenCode, pi, zcode, Hermes, and 3code.
GLM 5.3 is part of a 10-task harness bench.
GLM 5.3 is mentioned in the context of a benchmark alongside Claude, OpenCode, pi, zcode, Hermes, and 3code.
GLM 5.3 is mentioned in the context of a 10-task harness bench.
GLM 5.3 is part of a 10-task harness bench alongside Claude, OpenCode, pi, zcode, Hermes, and 3code.
GLM has a version named GLM 5.3.
GLM is listed alongside Claude, OpenCode, pi, zcode, Hermes, and 3code in a harness bench context.
GLM 5.3 is mentioned in a harness bench alongside Claude, OpenCode, pi, zcode, Hermes, and 3code.
GLM 5.3 is featured in a '10-task harness bench'.
The harness bench includes Claude, OpenCode, pi, zcode, Hermes, and 3code.
GLM has a version identified as GLM 5.3.
GLM has a version identifier '5.3'.
GLM is benchmarked or compared with Claude, OpenCode, pi, zcode, Hermes, and 3code.
GLM 5.3 is a version of GLM and is included in a 10-task harness bench alongside Claude, OpenCode, pi, zcode, Hermes, and 3code.
GLM is part of a 10-task harness bench.
GLM is part of a '10-task harness bench'.
GLM-5.3 achieved a score of 60 according to artificialanalysis.ai.
GLM-5.3 achieved a score of 60.
GLM-5.3 scored 60 according to artificialanalysis.ai.
GLM-5.3 has a score of 60 according to artificialanalysis.ai.
GLM-5.3's cost per task is $0.68.
GLM-5.3 costs $0.68 per task.
GLM-5.3 has a score of 60 on artificialanalysis.ai.
GLM-5.3 has a score of 60.
The cost per task for GLM-5.3 is $0.68.
GLM-5.3 has a score of 60, according to artificialanalysis.ai.
GLM is built for coding and research.
GLM is built for research and coding agents that plan, call tools for hours, and reason over large contexts.
GLM 5.3 is available.
Inference for GLM is supported.
GLM 5.3 is 2x-4x cheaper.
GLM 5.3 is for coding and research.
Inference is available for GLM.
GLM 5.3 is 2x-4x cheaper
GLM 5.3 is for coding and research
Inference is available for GLM
GLM is built for research and coding agents that plan, call tools for hours, and reason over large contexts
GLM 5.3 is 2x-4x cheaper for coding and research.
GLM supports inference.
GLM is built for research and coding agents.
GLM is built for agents that plan, call tools for hours, and reason over large contexts.
GLM 5.3 is mentioned.
GLM provides inference.
Built for research and coding agents that plan, call tools for hours, and reason over large contexts.
GLM 5.3
Inference for Kimi and GLM.
Inference for GLM is available.
Inference is built for GLM.
GLM is used for inference.
Inference for GLM is built for research and coding agents that plan, call tools for hours, and reason over large contexts.
Inference for GLM is built for research and coding agents.
zai-org provides a model named GLM-5.3-Flash-BF16.
There is a version of GLM called GLM-5.3-Flash-BF16.
zai-org offers a model named GLM-5.3-Flash-BF16.
A model named GLM-5.3-Flash-BF16 exists.
There is a model named GLM-5.3-Flash-BF16 from zai-org.
There is a version of GLM called GLM-5.3-Flash.
zai-org offers a model named GLM-5.3-Flash.
There is a model named GLM-5.3-Flash from zai-org.
A model named GLM-5.3-Flash exists.
zai-org provides a model named GLM-5.3-Flash.
Coinbase cut AI spending by 50% by switching to Chinese AI models GLM and Kimi.
Coinbase switched to Chinese AI models GLM and Kimi.
Switching to GLM (and Kimi) cuts AI spending by 50% for Coinbase.
Coinbase switches to Chinese AI models GLM and Kimi.
Coinbase switches to Chinese AI models GLM
Coinbase cuts AI spending by 50%
Coinbase cut AI spending by 50% after switching to GLM and Kimi.
Coinbase has switched to using the Chinese AI model GLM.
Switching to GLM and Kimi helped Coinbase cut its AI spending by 50%.
GLM is a Chinese AI model.
Coinbase switched to the Chinese AI model GLM.
The switch to GLM (and Kimi) helped Coinbase cut its AI spending by 50%.
Coinbase switched to using the Chinese AI model GLM.
Coinbase switched to GLM.
The use of GLM (and Kimi) helped Coinbase cut AI spending by 50%.
Coinbase cut its AI spending by 50% after switching to Chinese AI models GLM and Kimi.
Coinbase has switched to using Chinese AI models GLM and Kimi.
Coinbase switched to using GLM.
The switch to GLM and Kimi helped Coinbase cut AI spending by 50%.
Coinbase has switched to using Chinese AI models, including GLM.
Coinbase switches to Chinese AI Model GLM.
Coinbase has switched to GLM, a Chinese AI model.
GLM-4.7-Flash processes 12.4 tokens/second when used with HotPin.
GLM-4.7-Flash achieves 12.4 tokens/second when used with HotPin.
GLM-4.7-Flash has a disk size of 19.0GB.
GLM-4.7-Flash achieves 12.4 tokens/second using HotPin.
GLM-4.7-Flash achieves 12.4 tokens/second when run with HotPin.
Using HotPin with GLM-4.7-Flash results in a 30% RAM saving.
GLM-4.7-Flash has a minimum RAM requirement of 13.3GB when used with HotPin.
The output of GLM-4.7-Flash, when run with HotPin, is SHA-256 bit-identical to full-RAM runs.
GLM-4.7-Flash shows a 30% RAM saving when used with HotPin.
When run with HotPin, GLM-4.7-Flash has a token per second rate of 12.4.
The GLM-4.7-Flash model achieves 12.4 tokens per second with HotPin.
HotPin provides a 30% RAM saving for GLM-4.7-Flash.
The GLM-4.7-Flash model requires 13.3GB of minimum RAM when used with HotPin.
GLM-4.7-Flash achieves 12.4 tokens/second with HotPin.
HotPin provides 30% RAM savings for GLM-4.7-Flash.
GLM-4.7-Flash has a minimum RAM of 13.3GB when using HotPin.
There is a model named GLM-4.7-Flash.
HotPin provides a 30% RAM saving for the GLM-4.7-Flash model.
The GLM-4.7-Flash model requires 13.3GB of minimum RAM when using HotPin.
The GLM-4.7-Flash model has a disk size of 19.0GB.
The GLM-4.7-Flash model achieves 12.4 tokens per second when used with HotPin.
When run with HotPin, GLM-4.7-Flash requires a minimum RAM of 13.3GB.
GLM-4.7-Flash has a disk footprint of 19.0GB.
When run with HotPin, GLM-4.7-Flash achieves a token generation speed of 12.4 tokens per second.
When run with HotPin, GLM-4.7-Flash results in a 30% saving in RAM usage.
GLM-4.7-Flash is a Mixture of Experts (MoE) model.
GLM-4.7-Flash requires a minimum of 13.3GB RAM using HotPin.
The GLM-4.7-Flash model achieves a 30% RAM saving when used with HotPin.
GLM-4.7-Flash has a minimum RAM usage of 13.3GB.
GLM-4.7-Flash shows a -30% RAM savings when used with HotPin.
GLM-4.7-Flash requires a minimum RAM of 13.3GB when used with HotPin.
When run with HotPin, GLM-4.7-Flash shows a 30% saving in RAM usage.
GLM-4.7-Flash is a model with a disk size of 19.0GB.
Subjective claims voiced about GLM, each tagged with its polarity and linked to where it was said. Opinions from the record — never folded into the number.
The GLM coding agent, specifically ZCode, silently uploads Git history.
The GLM coding agent (ZCode) silently uploads Git history.
The GLM coding agent silently uploads your Git history.
The GLM coding agent (ZCode) silently uploads your Git history.
The GLM coding agent, ZCode, silently uploads Git history.
Kimi K3 and GLM-5.3 are better than Gemini 3.8 Flash.
Gemini 3.8 Flash was better in terms of Cost per task than GLM-5.3.
GLM-5.3 is better than Gemini 3.8 Flash.
Gemini 3.8 Flash was better than GLM-5.3 in terms of Cost per task.
GLM-5.3 is more intelligent than the new Gemini 3.8 Flash.
GLM-5.3 is not as good as Gemini 3.8 Flash in terms of Cost per task.
Kimi K3 and GLM-5.3 are more intelligent than the new Gemini 3.8 Flash.
Kimi K3 and GLM-5.3 are more intelligent than the new Gemini 3.8 Flash, based on artificialanalysis.ai.
GLM-5.3 is not as good as Gemini 3.8 Flash in terms of Cost per task, costing $0.68 compared to Gemini 3.8 Flash's $0.58.
GLM 5.3 is 2x-4x cheaper for coding and research.
GLM 5.3 is 2x-4x cheaper.
2x-4x cheaper GLM 5.3 for coding and research
Switching to GLM (and Kimi) allowed Coinbase to cut AI spending by 50%.