none reviewed yet · 4 benchmark observations · latest capture Sep 8, 2026
Inspect the evidenceZ.ai · MODEL PROFILE
GLM-5.3
Agentic coding teams that want near-frontier terminal/SWE performance with open weights and low cost
Saved editorial fit for your current task lens; not a benchmark result
How scoring worksVerified rates (Sep 8, 2026) · 100 runs / month at your token settings
Adjust workloadAt a glance
9 facts- Provider
- Z.ai
- Type
- API model
- Access
- Z.ai API, GLM Coding Plan, ZCode, Claude Code, OpenCode, Alibaba Cloud Model Studio resale, Hugging Face weights
- Context
- 1,048,576 tokens
- Maximum output
- 163,840 tokens maximum generation length (Z.ai); 128K used for Terminal Bench 3.0
- License / weights
- Open weights
- Input modalities
- text
- Output modalities
- text
- Pricing notes
- $1.40 in / $4.40 out per 1M with $0.26 cached input (Z.ai docs; cached-input storage free for a limited time). The GLM Coding Plan uses points, with 50% off-peak discount outside 14:00-18:00 UTC+8 on weekdays.
The practical trade-offs
Documented strengths
- Terminal Bench 2.1 88.2 is effectively tied with Kimi K3 (88.3) and DeepSeek V4 Pro (87.9)
- Huge generational jump: Terminal Bench 3.0 4.6 -> 28.3 and DeepSWE 46.2 -> 66.9 vs GLM-5.2
- Open weights (753B) with wide inference-engine support and $1.40/$4.40 hosted pricing
- TTFT 2.14 s with 84.2 tok/s - responsive for a frontier-scale model
Limitations to check
- No SWE-bench Pro, SWE-bench Verified or Design Arena row exists for 5.3
- Thinking cannot be disabled, forcing a migration for non-thinking apps
- Licence terms are not stated on the Hugging Face card; AA calls it a restricted commercial licence
- Text-only on the evidence available - no documented image input for frontend screenshots
Follow the source
6 source linksEvidence & conditions
6Source links
NoneReviewed records
4Benchmark runs
Sep 8, 2026Latest capture
- Evidence source 1
z.aiDate not recorded - Evidence source 2
huggingface.coDate not recorded - Evidence source 3
docs.z.aiDate not recorded - Evidence source 4
arena.aiDate not recorded - Evidence source 5
artificialanalysis.aiDate not recorded - Evidence source 6
docs.qwencloud.comDate not recorded
Benchmark observations
Terminal-Bench 2.1 Inspect conditions
- name
- Terminal-Bench 2.1
- value
- 88.2
- unit
- %
- source Url
- https://huggingface.co/zai-org/GLM-5.3
- checked At
- 2026-09-08T19:28:18Z
- attribution
- provider-reported
- configuration
- GLM-5.3; Claude Code 2.1.207; default max effort; temperature=1; top_p=1; max_new_tokens=65536; six-hour limit.
Terminal-Bench 3.0 Inspect conditions
- name
- Terminal-Bench 3.0
- value
- 28.3
- unit
- %
- source Url
- https://huggingface.co/zai-org/GLM-5.3
- checked At
- 2026-09-08T19:28:18Z
- attribution
- provider-reported
- configuration
- GLM-5.3; Claude Code 2.1.207; max effort; 400K context; 128K output; avg@3; 600 turns; ten-hour limit; ToolSearch disabled.
DeepSWE v1.1 Inspect conditions
- name
- DeepSWE v1.1
- value
- 66.9
- unit
- %
- source Url
- https://huggingface.co/zai-org/GLM-5.3
- checked At
- 2026-09-08T19:28:18Z
- attribution
- provider-reported
- configuration
- GLM-5.3; mini-SWE-agent; temperature=0.95; top_p=1; six-hour limit; 400K context.
Arena WebDev Frontend Inspect conditions
- name
- Arena WebDev Frontend
- value
- 1617
- unit
- arena_score
- source Url
- https://arena.ai/leaderboard/code/webdev/frontend
- checked At
- 2026-09-08T19:28:18Z
- attribution
- benchmark-publisher
- configuration
- Exact row glm-5.3-max; source results dated 2026-09-05; human preference; confidence interval +/-14; 2315 votes. This is a checked source snapshot, not a newly run September 8 evaluation.
Source reports, measured results, and editorial assessments are separate evidence types. Source dates do not imply a new benchmark run. Capture dates are shown when recorded; otherwise we say the capture date was not recorded. Recorded dates are compared with this catalogue snapshot (Sep 11, 2026), not today’s date.
Method AIS-V2
How this page is assessed
Quality claims follow Method AIS-V2.
Money never buys rank — commercial relationships cannot change rank, eligibility, evidence quality, or publication timing.
Submit or claim a listing is free and does not skip the editorial queue.
Private · this device only