RankingEffort benchmarks

GLM-5.1 · Non-reasoning

Compare models

43 measured results · 5 effort settings · 33 benchmark/harness combinations

Model evidence and sources →

Change model

Model

Current configurationSources

Compare with

Choose a second model and its effort to see both profiles and benchmark differences below.

Compare withModel and configuration

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AGLM-5.1 · Non-reasoning2 of 7 capabilities supported

Gaps are unknown, not zero. Hollow points are preliminary.

Agentic
A39.8Preliminary
Hard reasoning
A11.9Supported
Coding
A23.2Preliminary
Human pref
Unknown
Knowledge
A11.1Supported
Multimodal
Unknown
Long context
A11.0Preliminary

Each profile belongs to the named configuration. Capability scores use a shared panel for all axes, distinct from the overall ranking panel; they are not accuracy percentages or direct head-to-head wins.

Capability score evidence

GLM-5.1 · Non-reasoning: 6.0 overall comparison score. Meets the overall evidence requirements.

5 areas measured. The available task mix affects this estimate; missing areas remain unknown.

Which sources carry the weight?

Artificial Analysis · 75.5% direct comparison weight · independent of the model provider
Epoch AI · 24.5% direct comparison weight · independent of the model provider

Which benchmark families carry the weight?

FrontierMath · 24.5% direct comparison weight
IFBench · 10.2% direct comparison weight
Humanity’s Last Exam · 10.0% direct comparison weight
GPQA · 10.0% direct comparison weight
Critpt · 9.8% direct comparison weight
Other families (4) · 35.5% direct comparison weight

These shares describe direct comparison weight, not fractions of the final score or confidence. Source balancing does not give every family equal weight or remove correlations between overlapping sources.

How sensitive is this score?

The audit removes one source at a time and refits against the same overall reference panel. These published results use the matching dataset audited 2026-10-23.

Both ranks use the same surviving configurations for each removal. The cohort starts with 444 configurations supported in the original audit, including separate effort settings. These are diagnostic positions, not the default leaderboard ranks. Eligibility is not rechecked after removal.

What changes when a source is removed?
Removed source	Rank before → after	Rank movement	Cohort remaining / lost support	Score after (change)
Artificial Analysis	163 → 163	No movement	203 remaining / 241 lost	4.5 (-1.5 points)
ARC Prize	231 → 229	Up 2	444 remaining / 0 lost	7.6 (+1.7 points)
Datacurve	231 → 231	No movement	444 remaining / 0 lost	4.7 (-1.3 points)
LiveCodeBench	231 → 231	No movement	444 remaining / 0 lost	5.9 (-0.0 points)
Scale	231 → 231	No movement	444 remaining / 0 lost	6.9 (+1.0 points)
Terminal-Bench	231 → 231	No movement	444 remaining / 0 lost	5.9 (-0.0 points)
Cognition	231 → 233	Down 2	444 remaining / 0 lost	5.8 (-0.1 points)
LiveBench	230 → 230	No movement	443 remaining / 1 lost	6.1 (+0.2 points)
SWE-rebench	231 → 231	No movement	444 remaining / 0 lost	6.1 (+0.2 points)
Epoch AI	225 → 223	Up 2	431 remaining / 13 lost	6.4 (+0.4 points)
Vals AI	231 → 231	No movement	443 remaining / 1 lost	5.7 (-0.3 points)
Provider reports · Anthropic	231 → 231	No movement	444 remaining / 0 lost	6.0 (-0.0 points)
Provider reports · Moonshot AI	231 → 231	No movement	444 remaining / 0 lost	5.8 (-0.2 points)
Provider reports · Meta	231 → 231	No movement	444 remaining / 0 lost	5.9 (-0.0 points)
Provider reports · Mistral	231 → 231	No movement	444 remaining / 0 lost	6.0 (+0.0 points)
Provider reports · OpenAI	231 → 231	No movement	444 remaining / 0 lost	6.0 (+0.0 points)
All provider reports	231 → 231	No movement	444 remaining / 0 lost	5.8 (-0.1 points)

Lost support means a configuration no longer has a comparison path to the complete reference panel. Its rank is unavailable. A surviving path alone does not establish leaderboard eligibility.

Overlapping sources may remain correlated even with source balancing. Leave-one-source-out movement is a sensitivity diagnostic, not a spread of source-specific ranks or a confidence measure. Scoring methodology · Dated configuration audit

Every benchmark family

Removed evidence	Recomputed score	Change
critpt	7.4	+1.5
arc-agi	7.4	+1.4
deepswe	4.7	-1.3
epoch-game-puzzles	4.9	-1.0
tau-bench	5.1	-0.8
mmmu-pro	6.4	+0.5
omniscience	5.5	-0.5
terminal-bench	5.6	-0.4
aa-lcr	6.3	+0.4
gpqa	5.6	-0.4
frontiermath	6.2	+0.2
ifbench	6.2	+0.2
mmlu-pro	6.1	+0.2
simpleqa	6.1	+0.2
swe-rebench	6.1	+0.2
frontiercode	5.8	-0.1
livebench-instructions	6.1	+0.1
multi-swe-bench	5.8	-0.1
gdp-pdf	6.1	+0.1
livebench-language	6.0	+0.1
arc-agi-3	5.9	-0.1
apex-agents	6.0	+0.1
terminal-bench-science	6.0	+0.1
enigma-eval	5.9	-0.1
livebench-coding	5.9	-0.1
swe-atlas-qna	5.9	-0.1
harvey	5.9	-0.1
gmmlu	6.0	+0.1
analyst-agent	6.0	+0.0
itbench	5.9	-0.0
livebench-reasoning	5.9	-0.0
vibe-code	5.9	-0.0
automationbench	5.9	-0.0
briefcase	5.9	-0.0
swe-atlas-test-writing	5.9	-0.0
vals-finance-agent	5.9	-0.0
vals-legal-research	5.9	-0.0
vals-code-migration	5.9	-0.0
gdpval	5.9	-0.0
vals-tax-agent	5.9	-0.0
hle	5.9	-0.0
math500	6.0	+0.0
vals-excel-modeling	5.9	-0.0
livebench-math	6.0	+0.0
livecodebench	5.9	-0.0
enterprise-ops	6.0	+0.0
swe-atlas-refactoring	6.0	-0.0
livebench-data	6.0	+0.0
swe-bench-pro	6.0	+0.0
aime	6.0	-0.0

What evidence is missing from the fit?

Across all collected settings for this model: 99 observations, 26 contributing, 0 matched without graph weight and 73 excluded. Counts do not establish rank eligibility.

2 · Benchmark family or source protocol has not been reviewed
2 · Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode
13 · Effort is not identified
1 · Evaluator has not been reviewed for independent admission
25 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
28 · Supporting evidence outside the reviewed capability core
1 · Microsoft report Table 11 and section 4.1: MAI Terminal-Bench removes timeouts and uses a minimal ReAct harness; comparator values are cited from other model releases. A common evaluation protocol is not established.
1 · Narrow specialist biological, medical or security evaluation; preserved as raw evidence outside general capability scoring.

Inspect every observation and exclusion →

Benchmark results

These are published benchmark scores. Supported effort estimates also appear on the Capability leaderboard. Results from different harnesses occupy different rows. Missing cells stay unknown; no scores are copied between effort levels.

Benchmark / source	High	Max	Reasoning	Non-reasoning	Unspecified
AA-Briefcase EloArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Briefcase v1.1 is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-10-18.	Not reported	Not reported	964.54 Elo Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	Not reported	Not reported
AA-LCR v1.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	73.67% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	53.33% Reported settings GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning	Not reported
AutomationBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of task objectives completed with no guardrail violations · Higher is better · Benchmark developed by Zapier · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	20.31% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	Not reported	Not reported
CritPtArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Argonne and UIUC, with contributions from 60+ researchers globally. CritPt is under review by its authors following external feedback · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	4.57% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	0% Reported settings GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning	Not reported
GDP.pdf: All-pass RateArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of attempts where every atomic criterion passed · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	8.4% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	Not reported	Not reported
GDPval-AA v2.1 LeaderboardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Elo rating for performance on real-world work tasks · Anchored to DeepSeek V4.1 Flash (max) at 1600 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-10-18.	Not reported	Not reported	1,116.24 Elo Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	Not reported	Not reported
GPQA DiamondArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	86.77% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	83.94% Reported settings GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning	Not reported
Humanity's Last ExamArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	30.07% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	27.94% Reported settings GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning	Not reported
IFBenchArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	76.26% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	51.97% Reported settings GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning	Not reported
ITBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Combined public and private Site Reliability Engineering (SRE) tasks · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	40.25% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	Not reported	Not reported
AA-Omniscience IndexArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis Unit: index. Source collected 2026-10-18.	Not reported	Not reported	0.85 Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	-22.43 Reported settings GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning	Not reported
AA-Omniscience AccuracyArtificial Analysis · 6000 questions; 1 attempt; correct-answer share; GPT-5.6 Luna medium grader Benchmark details AA-Omniscience Accuracy (higher is better) measures the proportion of correctly answered questions out of all questions, regardless of whether the model chooses to answer · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	23.7% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	25.18% Reported settings GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning	Not reported
SciCodeArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark curated by scientists across 16 disciplines. SciCode is under review following an independent audit of the dataset · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	44.79% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	Not reported	Not reported
𝜏²-Bench TelecomArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	97.66% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	97.08% Reported settings GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning	Not reported
𝜏³-BankingArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Sierra Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	13.61% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	Not reported	Not reported
Terminal-Bench HardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	43.18% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	35.61% Reported settings GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning	Not reported
Terminal-Bench v2.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by the Laude Institute and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	61.8% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	Not reported	Not reported
Terminal-Bench v4.0Artificial Analysis · mini-SWE-agent v2.4.6; 66 tasks; pass@1 averaged over 3 repeats; 500 steps; task timeout up to 8 hours Benchmark details Benchmark developed by the Laude Institute, Stanford, and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	2.02% Reported settings GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1	Not reported	Not reported
Terminal-Bench 2.1Terminal-Bench · Claude Code Benchmark details Original public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-10-18.	Not reported	58.65% Reported settings GLM-5.1; Reported effort: max; 445 trials; recorded 2026-03-27	Not reported	Not reported	Not reported
Epoch · Chess Puzzles · v2.0.0Epoch AI · Epoch AI Inspect; task 2.0.0; scorer exact Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	20% Reported settings Epoch AI Inspect; task 2.0.0; scorer exact; model=glm-5.1; run=R7XgJMi2R9sv7tZdx5SZTv; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · FrontierMath Tiers 1–3 · v2.0.0Epoch AI · Epoch AI Inspect; task 2.0.0; scorer verification_code Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. FrontierMath was developed with OpenAI funding and unequal access to part of the question set; this result is from Epoch's evaluation. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	24.91% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.1_none; run=4hmmfwG9tgZJvKhL78nKzL; mean accuracy; https://epoch.ai/data/benchmarks.csv	36.84% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.1; run=Mhwme9odWJMzMjoYkW8r6B; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · GPQA diamond · v1.0.11Epoch AI · Epoch AI Inspect; task 1.0.11; scorer choice Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	89.9% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=glm-5.1; run=CBbeMKRRSeRsXnvSfn7Png; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · OTIS Mock AIME 2024-2025 · v1.1.6Epoch AI · Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	93.33% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.1; run=b7Lw9ExxAhVY3hdExoh4MP; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · SimpleQA Verified · v1.2.0Epoch AI · Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	34% Reported settings Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=glm-5.1; run=R2fMFAtRXah864hMifdQGV; mean accuracy; https://epoch.ai/data/benchmarks.csv
Vals AI · Finance Agent v2Vals AI · Vals FAB v2 shared six-tool harness; two-hour task limit Benchmark details Overall weighted rubric accuracy, averaged over three runs on 450 tasks. Dealbreaker failures and timeouts score zero. Related categories and all-pass scores are not additional votes. Three-model judge panel; private test set. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	44.79% Reported settings {"checkpoint":"glm-5.1","evaluatorModel":"zai/glm-5.1","sourceUpdatedOn":"2026-10-16","reasoning_effort":null,"compute_effort":null,"reasoning":null,"temperature":1,"top_p":0.95,"max_output_tokens":131072,"verbosity":null,"provider":"Zhipu AI","harness":null}

What these comparisons mean

Each source reports its own effort labels. Matching labels do not establish equal compute budgets or identical fallback behavior. Open Reported settings to inspect the exact model name, agent and task coverage. Multiple results at one level remain visible rather than selecting the best. Source-reported None or Non-reasoning labels are not treated as evidence that an API supports those settings.

These measurements use their own dated source collection. The leaderboard fits identified configurations jointly; it contains no pooled model ratings. Explicit thinking budgets are separate configurations. Read the methodology.

Download all effort benchmark results · 8,916 results across 259 models · Collected 2026-10-18

GLM-5.1 · Non-reasoning

Compare with

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context

Capability score evidence

Benchmark results