GLM-5.3: score and benchmark evidence
Historical release · · Z.ai
101.6 points · Rank 10 among 19 ranked models · Stability range 90.8–113.9 points.
Rank follows the point estimate; it does not establish statistically significant superiority. The scale is anchored at mean 100, SD 15 in the frozen calibration cohort, not human IQ or a percentage.
One capability score combines evidence across seven equally weighted domains. Related benchmark variants share a family budget, and influence from one evaluator is capped.
Release tli-2026-v1.0-2026-09-06. Methodology and limitations for this release.
This page preserves historical evidence. See the current model record.
Capability domains
Domain scores use calibration-cohort standard-deviation units. Unmeasured domains are shown as unavailable, not zero.
| Domain | Score (SD units) | Observed benchmarks |
|---|---|---|
| Knowledge & reasoning | -0.16 | 8 |
| Coding & software engineering | 0.17 | 11 |
| Agentic tool & computer use | 0.07 | 4 |
| Professional & real-world work | 0.14 | 12 |
| Multimodal & vision | -0.09 | 1 |
| Cybersecurity | -0.09 | 1 |
| Preference & communication | 0.24 | 2 |
Published benchmark evidence
39 results contribute to this score, from 56 collected results and 37 contributing benchmark families. Counts are not independent sample sizes.
Collected means a numeric result exists in the database. Used means its source, exact model checkpoint and benchmark protocol have been reviewed and its benchmark has a frozen calibration supported by multiple providers. For each benchmark we select the highest published aggregate across comparable reasoning modes, not necessarily maximum effort, and count it once. More tested settings provide more chances to record a high score; this selection advantage is not corrected by the conditional interval. Developer-reported and sole/unspecified settings remain eligible and disclosed. Unresolved does not mean false or useless: conflicting metrics, unverified citations and unmatched versions stay collected until reconciled.
The bar estimates score stability under the scoring assumptions: a fixed calibration and comparable benchmark availability. It resamples benchmark families and evaluators while keeping each domain’s evidence strength fixed, then adds a frozen correction learned from missing-evidence tests. Benchmark count and domain coverage both affect that correction. It does not add a second full capability-posterior draw or uncertainty from changing the reference calibration. It is not a guarantee under selective publication, new benchmark domains or future model releases.
Reporting sensitivity: ±1.4 points. Sensitivity to selectively published results. This stress range is not a confidence interval or a probability statement.
GDPval-AA v2 (Elo): 1679.47 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3 (max); Artificial Analysis published evaluation harness
Metric: Elo
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
Terminal-Bench 2.1: 83.895131%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3 (max); Artificial Analysis published evaluation harness
Metric: pass@1, AA harness
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
DeepSWE v1.1: 68.957871%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: glm-5-3; max; mini-swe-agent
Metric: pass@1 over scored rollout attempts
Original source · Retrieved 2026-09-06
Selected the best pass@1 across published reasoning efforts within mini-swe-agent. Pass@4 is not substituted.
LMArena (Chatbot Arena) — Text: 1482.03722 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: glm-5.3-max; Arena text overall; style control enabled
Metric: style-controlled text overall Elo
Original source · Retrieved 2026-09-06
Best published reasoning-mode rating within the same text overall board. Different leaderboard slices and undated earlier DeepSeek checkpoints are not pooled.
AA Intelligence Index v4.1.1 (score): 60 native-points
Not used in the score. Source category not recorded. Review status: excluded.
Held-out composite, never a scoring input
GPQA Diamond: 91.717172%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3 (max); Artificial Analysis published evaluation harness
Metric: accuracy, AA
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
AA-LCR: 76.33%
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: GLM-5.3 (max)
Original source · Retrieved 2026-09-06
Current AA result is LCR v1.1. The inherited AA-LCR row has no reviewed version match; a new version cannot silently substantiate the older value.
Finance Agent v2 — Vals: 55.84%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: fabv2 overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Excel Modeling Benchmark — Vals: 56.34%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: emb overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
SciCode: 59.027778%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3 (max); Artificial Analysis published evaluation harness
Metric: accuracy, AA harness
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
Humanity's Last Exam (no tools): 42.261353%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3 (max); Artificial Analysis published evaluation harness
Metric: accuracy, no tools, AA
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
Legal Research Bench — Vals: 49.04%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: legal_research overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Harvey LAB (Vals): 8.33%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: hlab overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
AA-Briefcase Overall Elo: 1518.58 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3 (max); Artificial Analysis published evaluation harness
Metric: overall Elo
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
MedScribe — Vals: 88.81%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: medscribe overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
SWE-bench Verified — Vals: 95.4%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: swebench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
LegalBench — Vals: 84.84%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: legal_bench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
TaxEval v2 — Vals: 72.36%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: tax_eval_v2 overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
KingBench 3: 91.25%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 91.25 for GLM-5.3 on KingBench 3 still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
Public Benefits Bench — Vals: 68.54%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: public-benefits-bench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
MedCode — Vals: 42.86%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: medcode overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
AutomationBench v1.0.6: 48.2%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 48.2 for GLM-5.3 on AutomationBench v1.0.6 still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
AA-Omniscience: 14.3 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3 (max); Artificial Analysis published evaluation harness
Metric: knowledge reliability index -100 to 100
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
MMLU Pro — Vals: 86.77%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: mmlu_pro overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
LiveBench: 76.13781%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: glm-5.3; LiveBench 2026-06-25 release
Metric: official overall: equal mean of seven category means
Original source · Retrieved 2026-09-06
Task mapping archived from categories_2026_06_25.json. Aggregate follows the official UI, not a flat mean of the 23 tasks. Undated old DeepSeek checkpoints excluded.
Code Migration †: 44.22%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: code-migration overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Toolathlon-Verified: 73%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 73 for GLM-5.3 on Toolathlon-Verified still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
Agents' Last Exam: 28.5%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 28.5 for GLM-5.3 on Agents' Last Exam still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
Terminal-Bench v3.0: 32.4%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3 (max); Claude Code
Metric: resolution rate on v3.0 task set
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
LiveCodeBench: 80.53%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: lcb overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
CyberGym: 84.5%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 84.5 for GLM-5.3 on CyberGym still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
Humanity's Last Exam w/ tools: 62.5%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 62.5 for GLM-5.3 on Humanity's Last Exam w/ tools still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
SWE-Marathon v1.1: 42.5%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 42.5 for GLM-5.3 on SWE-Marathon v1.1 still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
ProgramBench v1 (Raw Pass Rate) — Vals: 66.252%
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: zai/glm-5.3 · reasoning_effort=max
Metric: Raw Pass Rate: mean percent of hidden behavioral tests passed per task. Not Fully Resolved (all tests pass) and not Almost Resolved (≥95% of tests pass).
Original source · Retrieved 2026-09-05
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
SkillsBench †: 47.51%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: skillsbench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
FrontierSWE: 78.1%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 78.1 for GLM-5.3 on FrontierSWE still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
FrontierMath v2 Tier 4: 29.27%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 29.27 for GLM-5.3 on FrontierMath v2 Tier 4 still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
ExploitBench: 54.4%
Not used in the score. Source category not recorded. Review status: excluded.
Inherited comparator metric/scaffold equivalence to Astra Cap Percent is not established; the source flags possible contamination. Excluded pending protocol audit.
PostTrainBench: 39.8%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 39.8 for GLM-5.3 on PostTrainBench still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
Creative Writing v3: 2062.4 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: *GLM-5.3; published evaluation, effort unspecified
Metric: Creative Writing v3 Elo
Original source · Retrieved 2026-09-06
Exact checkpoint on the evaluator-hosted board. A starred model is externally submitted; it is not claimed as independently rerun by the benchmark owner.
NL2Repo: 58%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 58 for GLM-5.3 on NL2Repo still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
τ³-Banking: 50.309278%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3 (max); Artificial Analysis published evaluation harness
Metric: strict task success, AA
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
CritPt: 19.142857%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3 (max); Artificial Analysis published evaluation harness
Metric: accuracy, AA official grading
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
Terminal-Bench 4.0: 41.8%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3; max; Claude Code
Metric: resolution rate, v4.0.0 66 tasks
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
ProofBench v1.1 — Vals: 49%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: proof_bench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Vibe Code Bench v1.1 — Vals: 78.13%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: vibe-code overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
MineBench: 1850 native-points
Not used in the score. Source category not recorded. Review status: excluded.
Unresolved Pro/base model identities in source catalog; exclude until matched.
EnterpriseOps-Gym-AA: 36.44%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 36.44 for GLM-5.3 on EnterpriseOps-Gym-AA still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
MLCR-AA (Medical Long Context Reasoning): 48.333333%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3 (max); Artificial Analysis published evaluation harness
Metric: overall accuracy, AA
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
Vending-Bench 2: 8163.61 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3; Andon Labs Vending-Bench 2
Metric: arithmetic mean final bank balance USD after one simulated year
Original source · Retrieved 2026-09-06
Compare reasoning configurations using their mean over runs. Geometric mean, individual best runs, Fireworks Kimi endpoint, Vending Arena, and April DeepSeek Pro are not substituted.
CWE-bench: 31.1%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GLM-5.3; high; opencode
Metric: pass@1, 100 held-out audit-and-patch tasks
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Mystery Game Puzzles v1.0.4 — Epoch: 33%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 33 for GLM-5.3 on Mystery Game Puzzles v1.0.4 — Epoch still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
Tax Agent Bench v1 — Vals: 73.09%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: zai_glm-5.3; Vals max effort
Metric: tax_agent_bench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
RuneBench (30m, mean ln(1 + XP/min)): 5.001589 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: glm53
Metric: Arithmetic mean of ln(1 + peakXpRate) over all 16 skills, exactly as the owner’s Heatmap.js default ranking. Data rates are already normalized; do not divide by 200 again.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
VoxelBench (text-to-voxel, Glicko-2): 1786 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: GLM-5.3 (Max)
Metric: Glicko-2 rating from the text-to-voxel board; not win percentage, deviation, image-input mode or MineBench Elo.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
Code Arena WebDev (overall): 1609 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: glm-5.3-max
Metric: Published overall WebDev preference rating, not task success percentage or Arena Text score.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
Cite this model record
The Latent. “GLM-5.3: score and benchmark evidence.” 2026-09-06. Release tli-2026-v1.0-2026-09-06.
Download release data and definitions (JSON) · Data usage terms