Skip to content
ModelCap

GLM 5

All-versions archive #31Arena #51Open weights

Z.ai·z-ai/glm-5

GLM 5 is a language model published by Z.ai. 12 OpenRouter endpoints are published in the latest snapshot. It accepts text input and returns text. The published context limit is 205K tokens. The catalogue declares support for reasoning, tool use, structured outputs.

ModelCap Index · All-versions archive
79.6#31
Measured · 91% support · score interval 79.6–85.2
Market Gravity
51.2
Secondary market signal

Superseded by GLM 5.2. It no longer holds a current-board position; its all-versions archive rank is #31.

Input
$0.95
per 1M tokens
Output
$2.55
per 1M tokens
Context
205K
tokens
Providers
12
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
StreamLakefp8Cheapest$0.60$1.92198Kfp899.84%
GMICloudfp8$0.60$1.92203Kfp899.53%
DeepInfrafp4$0.60$2.08203Kfp499.84%
Baidufp8$0.70$2.24203Kfp898.60%
DigitalOcean$0.75$2.4064K—94.06%
SiliconFlowfp8$0.95$2.55205Kfp899.00%
AtlasCloudfp8$0.95$3.15203Kfp899.25%
Amazon Bedrock$1.00$3.20203K—99.64%
Novitafp8$1.00$3.20203Kfp899.67%
Z.AIfp8$1.00$3.20203Kfp898.91%
Venicefp8$1.00$3.20198Kfp8—
Phala$1.20$3.50203K——

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
deepinfra
live
$0.60$2.08203K996 ms28.7 tok/stools
novita
live
$1.00$3.20203K1098 ms39.4 tok/stools
featherless-ai
live
——————
zai-org
live · model author
———3294 ms37.6 tok/stools

Reported evaluation leads (16)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
cais/hle
hle
—30.5
Unpinned
not published
Reported
Quarantined
cais/hle
hle
—50.4
Unpinned
not published
Reported
Quarantined
collinear-ai/yc-bench
medium
—1,208,190
Unpinned
not published
Reported
Quarantined
harborframework/terminal-bench-2.0
terminal_bench
—52.4
Unpinned
not published
Reported
Quarantined
harborframework/terminal-bench-2.0
terminalbench_2
—52.4
Unpinned
not published
Reported
Quarantined
Idavidrein/gpqa
diamond
—86
Unpinned
not published
Reported
Quarantined
internlm/WildClawBench
overall
—42.6
Unpinned
not published
Reported
Quarantined
internlm/WildClawBench
avg_time
—373
Unpinned
not published
Reported
Quarantined
internlm/WildClawBench
avg_cost
—11.4
Unpinned
not published
Reported
Quarantined
MathArena/aime_2026
MathArena/aime_2026
—95.83
Unpinned
not published
Reported
Quarantined
MathArena/hmmt_feb_2026
MathArena/hmmt_feb_2026
—86.36
Unpinned
not published
Reported
Quarantined
mercor/apex-agents
apex-agents
—17.2
Unpinned
not published
Reported
Quarantined
mercor/APEX-v1-extended
apex-v1
—49
Unpinned
not published
Reported
Quarantined
SWE-bench/SWE-bench_Verified
swe_bench_%_resolved
—72.8
Unpinned
not published
Reported
Quarantined
SWE-bench/SWE-bench_Verified
swe_bench_%_resolved
—77.8
Unpinned
not published
Reported
Quarantined
TIGER-Lab/MMLU-Pro
mmlu_pro
—86
Unpinned
not published
Reported
Quarantined

Other versions (5)

ModelCap Index · All-versions archive

Methodology
79.6
Measured · 4 public benchmark observations across 4 boards
All-versions archive
#31
Public rank basis
Measured (measured)
Index support
90.6% · strong
Index interval
79.6–85.2
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · z-ai/z-ai/glm-5 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata zai-org/GLM-5@4e6698ba8e85059d749020e3c4d2123719f23926 (not the evaluation revision)
Direct benchmark observations
4
Breadth-adjusted BES point estimate
82.4
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
82.4
Evidence status
confirmed · 94% mass
General preference
84.7
Coding
83.0
Agents & tools
—
Reasoning
35.3
Evidence breadth
95%
Evidence coverage
91%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
28.4
Liquidity (providers × uptime)
95.6
Open reach (HF downloads)
61.1
Surface (context / tools / modalities)
73.5
Freshness
50.9
  • · OpenRouter popularity #59
  • · 12 live providers
  • · HF 30d downloads 155821
  • · Catalogue: context 204800, reasoning, tools
  • · First seen 2026-02-11

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
90.7
strong · 94% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
96.0
Evaluation provenance
81.8

Missing: artifactReproducibility.base-lineage, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
51.2
OpenRouter weekly popularity
#59 of 298

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
Arena
Official rank
#51 of 385
Rating
1456.7
95% confidence interval
1452–1461
Votes
28K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
28.4

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
95.6

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
61.1

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
50.9

Time since first public availability, on a six-month half-life.

Specification

Context window
205K tokens
Max output
131K tokens
Inputs
Text
Outputs
Text
Tokenizer
Other
Cached input tokens
$0.20 / 1M
First seen on OpenRouter
11 Feb 2026

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
mit
Pinned revision
4e6698ba8e85
Parameters
753.9B
Architecture
GlmMoeDsaForCausalLM
Model type
glm_moe_dsa
Hugging Face downloads (30d)
156K
Downloads (all time)
1.3M
Likes
2K
Repository
zai-org/GLM-5
Repository updated
5 Apr 2026, 07:48 UTC