Skip to main content

Model comparison

GLM-5 vs GLM-5.2

Data verified

Head-to-head evidence from 24 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Sibling matchup inside the GLM-5 family.

Z.AI
66.06/100
Margin
2.1pts
← winning
63.96/100
2 category wins2 category wins

Public leaderboard positions: GLM-5 #28 (Supported); GLM-5.2 #37 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GLM-5 and GLM-5.2 share 24 comparable benchmark results. 4 of 8 categories are comparable. 25 results are unique to GLM-5; 19 to GLM-5.2.

Updated July 23, 2026
Shared results
24
GLM-5 only
25
GLM-5.2 only
19
Comparable categories
4 / 8

GLM-5 makes more sense if knowledge is the priority or you want the cheaper token bill, while GLM-5.2 is the cleaner fit if mathematics is the priority or you need the larger 1M context window.

Confidence note. This is a partial-evidence comparison with 24 shared benchmark results across 7 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

GLM-5 and GLM-5.2 sit in the same GLM-5 family. This page is less about two unrelated model lineages and more about how the siblings trade off on benchmark shape, token costs, and practical limits like context window.

GLM-5 has the cleaner BenchAlign overall profile here, landing at 66.06 versus 63.96. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

GLM-5's sharpest advantage is in knowledge, where it averages 66.4 against 59.6. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 56.2% to 81%. GLM-5.2 does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.

GLM-5.2 is also the more expensive model on tokens at $1.40 input / $4.40 output per 1M tokens, versus $1.00 input / $3.20 output per 1M tokens for GLM-5. GLM-5.2 is the reasoning model in the pair, while GLM-5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GLM-5.2 gives you the larger context window at 1M, compared with 200K for GLM-5.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for GLM-5 and GLM-5.2
CategoryGLM-5ΔGLM-5.2
MathGLM-556.3Margin 39.6GLM-5.295.9
AgenticGLM-556.2Margin 24.8GLM-5.281.0
KnowledgeGLM-566.4Margin 6.8GLM-5.259.6
CodingGLM-566.3Margin 4.2GLM-5.262.1
ReasoningGLM-560.8MarginNo overlapGLM-5.2Not measured
MultilingualGLM-583.1MarginNo overlapGLM-5.2Not measured
Inst. FollowingGLM-592.6MarginNo overlapGLM-5.2Not measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · GLM-5B · GLM-5.2
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 56.2%B 81%
    Winner: GLM-5.2Δ 24.8
    Terminal-Bench 2.0: GLM-5 scored 56.2%; GLM-5.2 scored 81%. GLM-5.2 wins this benchmark.
  2. SWE-bench Pro

    Coding
    Source ↗
    A 55.1%B 62.1%
    Winner: GLM-5.2Δ 7
    SWE-bench Pro: GLM-5 scored 55.1%; GLM-5.2 scored 62.1%. GLM-5.2 wins this benchmark.
  3. HMMT Feb 2026

    Math
    Source ↗
    A 86.4%B 92.5%
    Winner: GLM-5.2Δ 6.1
    HMMT Feb 2026: GLM-5 scored 86.4%; GLM-5.2 scored 92.5%. GLM-5.2 wins this benchmark.
  4. GPQA

    Knowledge
    Source ↗
    A 86%B 91.2%
    Winner: GLM-5.2Δ 5.2
    GPQA: GLM-5 scored 86%; GLM-5.2 scored 91.2%. GLM-5.2 wins this benchmark.
  5. HLE

    Knowledge
    Source ↗
    A 50.4%B 54.7%
    Winner: GLM-5.2Δ 4.3
    HLE: GLM-5 scored 50.4%; GLM-5.2 scored 54.7%. GLM-5.2 wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricGLM-5GLM-5.2Comparison
Input / output priceUSD per 1M tokensGLM-5$1 input / $3.2 outputGLM-5.2$1.4 input / $4.4 outputGLM-5 has the lower combined listed price.
Generation speedtokens per secondGLM-574 tok/sGLM-5.2Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGLM-51.64 sGLM-5.2Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensGLM-5200KGLM-5.21MGLM-5.2 lists the larger context window.

Benchmark Deep Dive

AgenticGLM-5.2 wins
BenchmarkGLM-5GLM-5.2Result
Terminal-Bench 2.0Source 56.2%81%GLM-5.2 leads
Claw-EvalSource 57.7%Not comparable
QwenClawBenchSource 54.1%Not comparable
τ³-bench resultsSource 65.6%Not comparable
DeepPlanningSource 14.6%Not comparable
ToolathlonSource 38%48.2%GLM-5.2 leads
MCP AtlasSource 31.1%76.8%GLM-5.2 leads
MCP-TasksSource 60.8%Not comparable
WideResearchSource 69.8%Not comparable
τ²-bench resultsSource 98.2%99.1%GLM-5.2 leads
CyberGymSource 43.2%Not comparable
APEX-Agents-AASource 14.5%33.7%GLM-5.2 leads
Gert LabsSource 50.99%Not comparable
AA Agentic IndexSource 43.1%Not comparable
GDPval-AASource 50.7%Not comparable
GDPval-AASource 1514Not comparable
ResearchClawBenchSource 20.7%Not comparable
AA BriefcaseSource 1260Not comparable
AA AutomationBenchSource 27.8%Not comparable
AA EnterpriseOps-GymSource 42.7%Not comparable
AA Harvey LABSource 91.0%Not comparable
AA ITBenchSource 42.7%Not comparable
AA Tau3 BankingSource 26.8%Not comparable
terminalBenchHardSource 50.8%Not comparable
aaTerminalBench21Source 77.9%Not comparable
CodingGLM-5 wins
BenchmarkGLM-5GLM-5.2Result
SWE-bench VerifiedSource 77.8%Not comparable
SWE-bench Verified*Source 72.8%Not comparable
SWE-bench ProSource 55.1%62.1%GLM-5.2 leads
SWE MultilingualSource 73.3%Not comparable
SWE-RebenchSource 62.8%Not comparable
React Native EvalsSource 74.8%Not comparable
AA-SciCodeSource 46.2%50.5%GLM-5.2 leads
NL2RepoSource 48.9%Not comparable
Terminal-Bench 2.0Source 81.0%Not comparable
ProgramBenchSource 63.7%Not comparable
cursorBench32Source 55.0%Not comparable
AA Coding IndexSource 68.8%Not comparable
Reasoning
BenchmarkGLM-5GLM-5.2Result
LongBench v2Source 60.8%Not comparable
AI-NeedleSource 63.3%Not comparable
AA-LCRSource 63.3%71.3%GLM-5.2 leads
CritPtSource 2.0%20.9%GLM-5.2 leads
KnowledgeGLM-5 wins
BenchmarkGLM-5GLM-5.2Result
GPQASource 86%91.2%GLM-5.2 leads
GPQA-DSource 86.0%91.2%GLM-5.2 leads
SuperGPQASource 66.8%Not comparable
MMLU-ProSource 85.7%Not comparable
MMLU-Pro (Arcee)Source 85.8%Not comparable
HLESource 50.4%54.7%GLM-5.2 leads
Artificial Analysis Intelligence IndexSource 39.5%51.1%GLM-5.2 leads
AA-GPQA DiamondSource 82.0%89.5%GLM-5.2 leads
AA-HLESource 27.2%40.1%GLM-5.2 leads
AA-Omniscience IndexSource 2.0%4.0%GLM-5.2 leads
AA-Omniscience AccuracySource 26.9%25.1%GLM-5 leads
AA-Omniscience Hallucination RateSource 34.0%28.1%GLM-5.2 leads
HLE w/o toolsSource 40.5%Not comparable
AA Openness IndexSource 44.4%Not comparable
MathGLM-5.2 wins
BenchmarkGLM-5GLM-5.2Result
AIME26Source 95.8%99.2%GLM-5.2 leads
AIME25 (Arcee)Source 93.3%Not comparable
HMMT Feb 2025Source 97.5%Not comparable
HMMT Nov 2025Source 96.9%94.4%GLM-5 leads
HMMT Feb 2026Source 86.4%92.5%GLM-5.2 leads
MMAnswerBenchSource 82.5%91.0%GLM-5.2 leads
FrontierMath v2 (Tiers 1-3)Source 16.434%Not comparable
FrontierMath v2 (Tier 4)Source 2.100%Not comparable
Multilingual
BenchmarkGLM-5GLM-5.2Result
MMLU-ProXSource 83.1%Not comparable
NOVA-63Source 55.1%Not comparable
Multimodal
BenchmarkGLM-5GLM-5.2Result
Design Arena WebsiteSource 12781340GLM-5.2 leads
Inst. Following
BenchmarkGLM-5GLM-5.2Result
IFEvalSource 92.6%Not comparable
AA-IFBenchSource 72.3%73.3%GLM-5.2 leads
Frequently Asked Questions (5)

Which is better, GLM-5 or GLM-5.2?

GLM-5 and GLM-5.2 are sibling variants in the GLM-5 family, so the right pick depends on whether you value the better benchmark line, cheaper tokens, or the larger context window. GLM-5 is ahead on BenchLM's BenchAlign leaderboard 66.06 to 63.96.

Which is better for knowledge tasks, GLM-5 or GLM-5.2?

GLM-5 has the edge for knowledge tasks in this comparison, averaging 66.4 versus 59.6. Inside this category, AA-HLE is the benchmark that creates the most daylight between them.

Which is better for coding, GLM-5 or GLM-5.2?

GLM-5 has the edge for coding in this comparison, averaging 66.3 versus 62.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, GLM-5 or GLM-5.2?

GLM-5.2 has the edge for math in this comparison, averaging 95.9 versus 56.3. Inside this category, MMAnswerBench is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GLM-5 or GLM-5.2?

GLM-5.2 has the edge for agentic tasks in this comparison, averaging 81 versus 56.2. Inside this category, MCP Atlas is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.