RankingEffort benchmarks

GLM-5.2 · Max effort benchmarks

Compare measured Low, Medium, High and other settings. Every number keeps its source.

Model

GLM-5.2

65 measured results · 7 reported effort labels · 44 benchmark/harness combinations. Model evidence and sources →

Capability score evidence

GLM-5.2 · Max: 29.1 overall comparison score. Meets the overall evidence requirements.

Which sources carry the weight?

Artificial Analysis · 26.2% direct comparison weight · independent
Epoch AI · 20.2% direct comparison weight · independent
Moonshot AI · 19.3% direct comparison weight · provider report
Datacurve · 19.1% direct comparison weight · independent
Vals AI · 15.2% direct comparison weight · independent

These shares describe the comparisons entering the fit, not fractions of the final score.

How sensitive is this score?

Remove one evaluator or family and refit the graph against the same overall panel. Values use the matching dataset audited 2026-09-12. These are sensitivity checks, not confidence intervals; ranking eligibility may also change.

Removed evidence	Recomputed score	Change
Artificial Analysis	27.9	-1.2
ARC Prize	31.5	+2.3
Datacurve	27.8	-1.3
LiveCodeBench	29.1	-0.0
Scale	30.7	+1.5
Terminal-Bench	29.1	-0.0
Cognition	29.8	+0.7
LiveBench	29.9	+0.8
SWE-rebench	28.9	-0.2
Epoch AI	30.1	+0.9
Vals AI	27.4	-1.7
Provider reports · Anthropic	29.2	+0.0
Provider reports · Moonshot AI	31.1	+2.0
Provider reports · Meta	29.1	-0.0
Provider reports · Mistral	29.1	+0.0
All provider reports	31.1	+2.0

Every benchmark family

Removed evidence	Recomputed score	Change
arc-agi	31.4	+2.2
gpqa	27.9	-1.3
harvey	27.9	-1.2
simpleqa	30.3	+1.1
deepswe	28.1	-1.0
mmmu-pro	30.0	+0.8
frontiercode	29.8	+0.7
mmlu-pro	29.8	+0.7
frontiermath	28.6	-0.6
omniscience	29.7	+0.5
vals-code-migration	28.8	-0.4
terminal-bench	29.5	+0.4
hle	29.5	+0.4
gdp-pdf	29.5	+0.3
itbench	28.9	-0.3
automationbench	29.4	+0.3
multi-swe-bench	28.9	-0.2
swe-rebench	28.9	-0.2
livebench-instructions	29.4	+0.2
apex-agents	28.9	-0.2
tau-bench	28.9	-0.2
swe-atlas-qna	28.9	-0.2
livebench-coding	29.0	-0.2
livebench-language	29.3	+0.2
aa-lcr	29.3	+0.2
vibe-code	29.3	+0.1
livebench-reasoning	29.0	-0.1
vals-excel-modeling	29.3	+0.1
enterprise-ops	29.0	-0.1
livebench-data	29.3	+0.1
briefcase	29.0	-0.1
enigma-eval	29.3	+0.1
arc-agi-3	29.0	-0.1
swe-atlas-test-writing	29.1	-0.1
aime	29.2	+0.1
scicode	29.2	+0.1
vals-finance-agent	29.2	+0.1
epoch-game-puzzles	29.1	-0.1
gdpval	29.1	-0.1
ifbench	29.1	-0.0
critpt	29.1	-0.0
swe-atlas-refactoring	29.1	-0.0
livebench-math	29.2	+0.0
gmmlu	29.2	+0.0
vals-legal-research	29.2	+0.0
analyst-agent	29.2	+0.0
livecodebench	29.1	-0.0
math500	29.2	+0.0
swe-bench-pro	29.1	-0.0

What evidence is missing from the fit?

Across all collected settings for this model: 122 observations, 64 contributing, 0 matched without graph weight and 58 excluded. Counts do not establish rank eligibility.

2 · Benchmark family or source protocol has not been reviewed
2 · The evaluator reports no named effort control. This does not identify a non-reasoning configuration.
3 · Effort is not identified
14 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
31 · Supporting evidence outside the reviewed capability core
3 · Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.
1 · Kimi K3 Evaluation Details cites GLM release blog, Artificial Analysis or OpenAI, per model; retain as published context, not a new Moonshot comparison.
1 · Kimi K3 Evaluation Details cites Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison.
1 · The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison.

Inspect every observation and exclusion →

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AGLM-5.2 · Max4 of 7 capabilities supported

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

Agentic
A41.4Supported
Hard reasoning
A41.2Supported
Coding
A31.4Supported
Human pref
Unknown
Knowledge
A20.1Supported
Multimodal
Unknown
Long context
A30.2Preliminary

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.

Compare this configuration →Explore the model evidence profile →

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	Minimal	Low	Medium	High	Max	Non-reasoning	Unspecified
AA-Briefcase EloArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Briefcase 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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	1,231.38 Elo Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	Not reported	Not reported
APEX-Agents-AAArtificial 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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	33.7% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	78.33% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	42.33% Reported settings GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	28.4% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	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 · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	20.86% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	3.14% Reported settings GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning	Not reported
EnterpriseOps-Gym-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Overall task success rate across all eight enterprise domains (oracle tool mode) · Benchmark developed by ServiceNow Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	42.73% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	Not reported	Not reported
GDP.pdf: All-passArtificial 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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	10.4% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	Not reported	Not reported
GDPval-AA v2 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 a human baseline of 1,000 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	1,406.07 Elo Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	1,306.43 Elo Reported settings GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning	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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	89.49% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	68.59% Reported settings GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning	Not reported
Harvey LAB-AA: Criterion Pass RateArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of atomic pass/fail rubric criteria the deliverables satisfy, graded by a single LLM judge · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	90.97% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	Not reported	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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	41.15% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	9.78% Reported settings GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	73.33% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	Not reported	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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	42.66% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	Not reported	Not reported
MLCR-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of tasks judged accurate, complete, and concise · Expert + compound (hard) sets · Benchmark developed by Wisedocs · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	7.22% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	4.43 Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	-6.57 Reported settings GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	24.33% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	20.28% Reported settings GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning	Not reported
SciCodeArtificial 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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	51.16% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	99.12% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	Not reported	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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	34.64% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	16.7% Reported settings GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning	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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	50.76% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	Not reported	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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	77.9% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	51.69% Reported settings GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning	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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	1.01% Reported settings GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2	Not reported	Not reported
DeepSWE v1.1Datacurve · mini-swe-agent Benchmark details Original public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	36.3% Reported settings glm-5-2; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs	43.8% Reported settings glm-5-2; Reported effort: max; 113 unique tasks; 450 attempts; 4 runs	Not reported	Not reported
FrontierCode 1.1 · extended-mini-swe-agentCognition · mini-swe-agent Benchmark details FrontierCode 1.1; mini-swe-agent. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	40.05% Reported settings FrontierCode 1.1; extended; 150 tasks; mini-swe-agent; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0 The evaluator reports no named effort control. This does not identify a non-reasoning configuration. Source label needs review
FrontierCode 1.1 · main-mini-swe-agentCognition · mini-swe-agent Benchmark details FrontierCode 1.1; mini-swe-agent. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	24.5% Reported settings FrontierCode 1.1; main; 100 tasks; mini-swe-agent; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0 The evaluator reports no named effort control. This does not identify a non-reasoning configuration. Source label needs review
SWE-rebench · 2026-03 · toolsSWE-rebench · SWE-rebench standardized ReAct tools Benchmark details Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	53.48% Reported settings SWE-rebench standardized ReAct tools; swe-rebench-2026-03-tools; GLM-5.2 [high]; checkpoint=glm-5.2	Not reported	Not reported	Not reported
SWE-rebench · 2026-04 · toolsSWE-rebench · SWE-rebench standardized ReAct tools Benchmark details Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	51.16% Reported settings SWE-rebench standardized ReAct tools; swe-rebench-2026-04-tools; GLM-5.2 [high]; checkpoint=glm-5.2	Not reported	Not reported	Not reported
SWE-rebench · 2026-05 · toolsSWE-rebench · SWE-rebench standardized ReAct tools Benchmark details Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	61.11% Reported settings SWE-rebench standardized ReAct tools; swe-rebench-2026-05-tools; GLM-5.2 [high]; checkpoint=glm-5.2	Not reported	Not reported	Not reported
SWE-rebench · 2026-06 · toolsSWE-rebench · SWE-rebench standardized ReAct tools Benchmark details Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	58.1% Reported settings SWE-rebench standardized ReAct tools; swe-rebench-2026-06-tools; GLM-5.2 [high]; checkpoint=glm-5.2	Not reported	Not reported	Not reported
Epoch · Chess Puzzles · 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 2026-09-12.	Not reported	14% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.2_low; run=FUE7jUup3RsXiXpYTjMKb5; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	21% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.2_max; run=G8hwpomZQaMniWH5XUzTRe; mean accuracy; https://epoch.ai/data/benchmarks.csv	6% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.2_none; run=kwT2PhMLMheWkxaqwh8PKq; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported
Epoch · FrontierMath Tier 4 · 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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	29.27% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.2_max; run=JebA8dYLVov6H49ZQSLXh5; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported
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 2026-09-12.	Not reported	54.74% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.2_low; run=UnKHyc2idtTmoTUGxGeNJV; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	59.21% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.2_max; run=TTuCPacMDpNaCSs3Hpbdjp; mean accuracy; https://epoch.ai/data/benchmarks.csv	42.46% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.2_none; run=ECdG3m8n5ABfWVZ55rPFmT; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported
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 2026-09-12.	Not reported	87.88% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=glm-5.2_low; run=SB6Qj6rCBDk8jZmFcCTzWc; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	91.86% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=glm-5.2_max; run=c5kpB4axzmygRywWqBKFmv; mean accuracy; https://epoch.ai/data/benchmarks.csv	71.21% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=glm-5.2_none; run=YDQJAMgMjLaikPkeVDbAjr; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported
Epoch · Mystery Game Puzzles · v1.0.4 · Tool submissionEpoch AI · Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_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 2026-09-12.	18% Reported settings Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=glm-5.2_minimal; run=aekViWbdqVVeXpEG5hrSbQ; mean accuracy; https://epoch.ai/data/benchmarks.csv	19% Reported settings Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=glm-5.2_low; run=7DQNxGG5q6i7VtnzF7vNxA; mean accuracy; https://epoch.ai/data/benchmarks.csv	15% Reported settings Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=glm-5.2_medium; run=NfN7VwMPjSVqViqrBQPWk2; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	18% Reported settings Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=glm-5.2_none; run=BLjXudxuEyLbZiKBSZz326; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported
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 2026-09-12.	Not reported	75.56% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.2_low; run=9uKmMPn6eiRPsfcLKod7M7; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	86.39% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.2_max; run=XjFqou6MyT2XLpkUsCrgxM; mean accuracy; https://epoch.ai/data/benchmarks.csv	28.89% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.2_none; run=J8hYKbXiGhetQRwu5bUSp6; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported
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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	34.2% Reported settings Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=glm-5.2_max; run=WgjFZzojpiv54XqUhvfuUG; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported
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 2026-09-12.	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	49.7% Reported settings {"checkpoint":"glm-5.2","evaluatorModel":"zai/glm-5.2","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":null,"reasoning":null,"temperature":null,"top_p":null,"max_output_tokens":null,"verbosity":null,"provider":"Zhipu AI","harness":null}
Vals AI · Code Migration v1Vals AI · Vals Code Migration shared agent harness Benchmark details Hidden behavior-test pass rate, equally weighted across 40 repositories (30 CLI and 10 COBOL-to-Java). Anti-cheat failures score zero. Code-quality ratings and language splits are not additional votes. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	37.87% Reported settings {"checkpoint":"glm-5.2","evaluatorModel":"zai/glm-5.2","sourceUpdatedOn":"2026-09-10","reasoning_effort":"max","compute_effort":null,"reasoning":null,"temperature":1,"top_p":0.95,"max_output_tokens":131072,"verbosity":null,"provider":"Zhipu AI","harness":null}	Not reported	Not reported
Vals AI · Legal Research Bench v1Vals AI · Vals Legal Research shared five-tool harness; three-hour task limit Benchmark details All-pass accuracy on 208 private legal research tasks. Every expert rubric check must pass; GPT-5.4 judges responses. Partial-credit scores and practice-area splits are not additional votes. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	31.25% Reported settings {"checkpoint":"glm-5.2","evaluatorModel":"zai/glm-5.2","sourceUpdatedOn":"2026-09-10","reasoning_effort":"max","compute_effort":null,"reasoning":null,"temperature":1,"top_p":0.95,"max_output_tokens":131072,"verbosity":null,"provider":"Zhipu AI","harness":null}	Not reported	Not reported
Vals AI · Excel Modeling Benchmark v1Vals AI · Vals EMB shared workbook agent harness; 3.5-hour task limit Benchmark details Mean of seven equally weighted task categories. Template submissions use recalculated Excel cell accuracy; scratch submissions use rubric checks judged by GPT-5.4 Mini XHigh. Partial credit does not mean task completion. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	61.53% Reported settings {"checkpoint":"glm-5.2","evaluatorModel":"zai/glm-5.2","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":null,"reasoning":null,"temperature":null,"top_p":null,"max_output_tokens":null,"verbosity":null,"provider":"Zhipu AI","harness":null}
Vals AI · MMLU-Pro v1Vals AI · Vals MMLU-Pro five-shot chain-of-thought; regex answer grading Benchmark details Mean accuracy across 14 subjects under Vals five-shot prompting. Subject splits share one family and are not additional votes. Vals labels this benchmark archived; it is historical corroboration, not ongoing frontier evaluation. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	86.71% Reported settings {"checkpoint":"glm-5.2","evaluatorModel":"zai/glm-5.2","sourceUpdatedOn":"2026-09-01","reasoning_effort":null,"compute_effort":null,"reasoning":null,"temperature":null,"top_p":null,"max_output_tokens":null,"verbosity":null,"provider":"Zhipu AI","harness":null}
Vals AI · Terminal-Bench 2.1Vals AI · Vals Terminus 2 harness; pass@1 on 89 tasks Benchmark details Overall task pass rate under the shared Terminus 2 configuration. All task tests must pass. Difficulty splits share one family. Fable 5 and Opus 5 mixed-checkpoint fallback runs are excluded. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	67.79% Reported settings {"checkpoint":"glm-5.2","evaluatorModel":"zai/glm-5.2","sourceUpdatedOn":"2026-09-10","reasoning_effort":"max","compute_effort":null,"reasoning":null,"temperature":1,"top_p":1,"max_output_tokens":48000,"verbosity":null,"provider":"Zhipu AI","harness":null}	Not reported	Not reported
Vals AI · Vibe Code Bench v1.1Vals AI · Vals modified OpenHands harness; five hours or 1,000 turns per app Benchmark details Mean app test pass rate on the canonical v1.1 test set. Browser Use executes workflow tests; each test requires at least 90% of its substeps. Automated judging can introduce error. Alternate agents are excluded. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	63.96% Reported settings {"checkpoint":"glm-5.2","evaluatorModel":"zai/glm-5.2","sourceUpdatedOn":"2026-09-10","reasoning_effort":"max","compute_effort":null,"reasoning":null,"temperature":1,"top_p":0.95,"max_output_tokens":131072,"verbosity":null,"provider":"Zhipu AI","harness":"OpenHands"}	Not reported	Not reported
Vals AI · Harvey Legal Agent Benchmark v1Vals AI · Vals Harvey held-out legal file-work protocol; internet disabled Benchmark details Mean task resolution across two judges (GPT-5.5 Medium and Sonnet 4.6), requiring every criterion to pass. Criteria pass rates and practice-area splits do not add votes. Shared Harvey family; Fable 5 fallback run excluded. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	7.08% Reported settings {"checkpoint":"glm-5.2","evaluatorModel":"zai/glm-5.2","sourceUpdatedOn":"2026-09-10","reasoning_effort":"max","compute_effort":null,"reasoning":null,"temperature":1,"top_p":0.95,"max_output_tokens":131072,"verbosity":null,"provider":"Zhipu AI","harness":null}	Not reported	Not reported

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 · 7,424 results across 240 models · Collected 2026-09-12

GLM-5.2 · Max effort benchmarks

GLM-5.2

Capability score evidence

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context