Skip to main content

Model comparison

GLM-5 vs Qwen 3.6 Max (preview)

Data verified

Head-to-head evidence from 18 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Z.AI
65.98/100
Margin
6.5pts
← winning
59.44/100
2 category wins2 category wins

Public leaderboard positions: GLM-5 #26 (Supported); Qwen 3.6 Max (preview) #54 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GLM-5 and Qwen 3.6 Max (preview) share 18 comparable benchmark results. 4 of 8 categories are comparable. 32 results are unique to GLM-5; 4 to Qwen 3.6 Max (preview).

Updated July 17, 2026
Shared results
18
GLM-5 only
32
Qwen 3.6 Max (preview) only
4
Comparable categories
4 / 8

Pick GLM-5 if you want the stronger benchmark profile. Qwen 3.6 Max (preview) only becomes the better choice if agentic is the priority or you need the larger 256K context window.

Confidence note. This is a partial-evidence comparison with 18 shared benchmark results across 6 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 is clearly ahead on the BenchAlign aggregate, 65.98 to 59.44. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GLM-5's sharpest advantage is in mathematics, where it averages 56.3 against 18.4. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 56.2% to 65.4%. Qwen 3.6 Max (preview) does hit back in agentic, so the answer changes if that is the part of the workload you care about most.

Qwen 3.6 Max (preview) 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. Qwen 3.6 Max (preview) gives you the larger context window at 256K, 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 Qwen 3.6 Max (preview)
CategoryGLM-5ΔQwen 3.6 Max (preview)
MathGLM-556.3Margin 37.9Qwen 3.6 Max (preview)18.4
CodingGLM-566.3Margin 15.3Qwen 3.6 Max (preview)51.0
AgenticGLM-556.2Margin 9.2Qwen 3.6 Max (preview)65.4
KnowledgeGLM-566.6Margin 7.3Qwen 3.6 Max (preview)73.9
ReasoningGLM-560.8MarginNo overlapQwen 3.6 Max (preview)Not measured
MultilingualGLM-583.1MarginNo overlapQwen 3.6 Max (preview)Not measured
Inst. FollowingGLM-592.6MarginNo overlapQwen 3.6 Max (preview)Not measured

Decisive benchmark drivers

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

More
A · GLM-5B · Qwen 3.6 Max (preview)
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 56.2%B 65.4%
    Winner: Qwen 3.6 Max (preview)Δ 9.2
    Terminal-Bench 2.0: GLM-5 scored 56.2%; Qwen 3.6 Max (preview) scored 65.4%. Qwen 3.6 Max (preview) wins this benchmark.
  2. SuperGPQA

    Knowledge
    Source ↗
    A 66.8%B 73.9%
    Winner: Qwen 3.6 Max (preview)Δ 7.1
    SuperGPQA: GLM-5 scored 66.8%; Qwen 3.6 Max (preview) scored 73.9%. Qwen 3.6 Max (preview) wins this benchmark.
  3. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 16.434%B 23.103%
    Winner: Qwen 3.6 Max (preview)Δ 6.7
    FrontierMath v2 (Tiers 1-3): GLM-5 scored 16.434%; Qwen 3.6 Max (preview) scored 23.103%. Qwen 3.6 Max (preview) wins this benchmark.
  4. SWE-bench Pro

    Coding
    Source ↗
    A 55.1%B 57.3%
    Winner: Qwen 3.6 Max (preview)Δ 2.2
    SWE-bench Pro: GLM-5 scored 55.1%; Qwen 3.6 Max (preview) scored 57.3%. Qwen 3.6 Max (preview) wins this benchmark.
  5. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 2.100%B 4.167%
    Winner: Qwen 3.6 Max (preview)Δ 2.1
    FrontierMath v2 (Tier 4): GLM-5 scored 2.100%; Qwen 3.6 Max (preview) scored 4.167%. Qwen 3.6 Max (preview) wins this benchmark.

Operational comparison

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

MetricGLM-5Qwen 3.6 Max (preview)Comparison
Input / output priceUSD per 1M tokensGLM-5$1 input / $3.2 outputQwen 3.6 Max (preview)Not availableA complete price comparison is not available.
Generation speedtokens per secondGLM-574 tok/sQwen 3.6 Max (preview)Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGLM-51.64 sQwen 3.6 Max (preview)Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensGLM-5200KQwen 3.6 Max (preview)256KQwen 3.6 Max (preview) lists the larger context window.

Benchmark Deep Dive

AgenticQwen 3.6 Max (preview) wins
BenchmarkGLM-5Qwen 3.6 Max (preview)Result
Terminal-Bench 2.0Source 56.2%65.4%Qwen 3.6 Max (preview) leads
Claw-EvalSource 57.7%Not comparable
QwenClawBenchSource 54.1%59.0%Qwen 3.6 Max (preview) leads
τ³-bench resultsSource 65.6%Not comparable
DeepPlanningSource 14.6%Not comparable
ToolathlonSource 38%Not comparable
MCP AtlasSource 31.1%Not comparable
MCP-TasksSource 60.8%Not comparable
WideResearchSource 69.8%Not comparable
τ²-bench resultsSource 98.2%95.9%GLM-5 leads
CyberGymSource 43.2%Not comparable
APEX-Agents-AASource 14.5%Not comparable
Gert LabsSource 50.99%Not comparable
QwenWebBenchSource 1532Not comparable
CodingGLM-5 wins
BenchmarkGLM-5Qwen 3.6 Max (preview)Result
SWE-bench VerifiedSource 77.8%Not comparable
SWE-bench Verified*Source 72.8%Not comparable
SWE-bench ProSource 55.1%57.3%Qwen 3.6 Max (preview) leads
SWE MultilingualSource 73.3%Not comparable
SWE-RebenchSource 62.8%Not comparable
React Native EvalsSource 74.8%Not comparable
Terminal-Bench HardSource 43.2%43.9%Qwen 3.6 Max (preview) leads
AA-SciCodeSource 46.2%46.9%Qwen 3.6 Max (preview) leads
SciCodeSource 47%Not comparable
NL2RepoSource 42.9%Not comparable
Terminal-Bench 2.0Source 65.4%Not comparable
Reasoning
BenchmarkGLM-5Qwen 3.6 Max (preview)Result
LongBench v2Source 60.8%Not comparable
AI-NeedleSource 63.3%Not comparable
AA-LCRSource 63.3%69.7%Qwen 3.6 Max (preview) leads
CritPtSource 2.0%3.7%Qwen 3.6 Max (preview) leads
KnowledgeQwen 3.6 Max (preview) wins
BenchmarkGLM-5Qwen 3.6 Max (preview)Result
GPQASource 86%Not comparable
GPQA-DSource 86.0%Not comparable
SuperGPQASource 66.8%73.9%Qwen 3.6 Max (preview) leads
MMLU-ProSource 85.7%Not comparable
MMLU-Pro (Arcee)Source 85.8%Not comparable
HLESource 50.4%Not comparable
Artificial Analysis Intelligence IndexSource 39.5%40.0%Qwen 3.6 Max (preview) leads
AA-GPQA DiamondSource 82.0%88.8%Qwen 3.6 Max (preview) leads
AA-HLESource 27.2%28.9%Qwen 3.6 Max (preview) leads
AA-Omniscience IndexSource 2.0%10.2%Qwen 3.6 Max (preview) leads
AA-Omniscience AccuracySource 26.9%37.7%Qwen 3.6 Max (preview) leads
AA-Omniscience Hallucination RateSource 34.0%44.2%GLM-5 leads
MathGLM-5 wins
BenchmarkGLM-5Qwen 3.6 Max (preview)Result
AIME26Source 95.8%Not comparable
AIME25 (Arcee)Source 93.3%Not comparable
HMMT Feb 2025Source 97.5%Not comparable
HMMT Nov 2025Source 96.9%Not comparable
HMMT Feb 2026Source 86.4%Not comparable
MMAnswerBenchSource 82.5%Not comparable
FrontierMath v2 (Tiers 1-3)Source 16.434%23.103%Qwen 3.6 Max (preview) leads
FrontierMath v2 (Tier 4)Source 2.100%4.167%Qwen 3.6 Max (preview) leads
Multilingual
BenchmarkGLM-5Qwen 3.6 Max (preview)Result
MMLU-ProXSource 83.1%Not comparable
NOVA-63Source 55.1%Not comparable
Multimodal
BenchmarkGLM-5Qwen 3.6 Max (preview)Result
Design Arena WebsiteSource 1282Not comparable
Inst. Following
BenchmarkGLM-5Qwen 3.6 Max (preview)Result
IFEvalSource 92.6%Not comparable
AA-IFBenchSource 72.3%76.6%Qwen 3.6 Max (preview) leads
Frequently Asked Questions (5)

Which is better, GLM-5 or Qwen 3.6 Max (preview)?

GLM-5 is ahead on BenchLM's BenchAlign leaderboard, 65.98 to 59.44. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 56.2% and 65.4%.

Which is better for knowledge tasks, GLM-5 or Qwen 3.6 Max (preview)?

Qwen 3.6 Max (preview) has the edge for knowledge tasks in this comparison, averaging 73.9 versus 66.6. Inside this category, AA-Omniscience Accuracy is the benchmark that creates the most daylight between them.

Which is better for coding, GLM-5 or Qwen 3.6 Max (preview)?

GLM-5 has the edge for coding in this comparison, averaging 66.3 versus 51. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, GLM-5 or Qwen 3.6 Max (preview)?

GLM-5 has the edge for math in this comparison, averaging 56.3 versus 18.4. Inside this category, FrontierMath v2 (Tiers 1-3) is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GLM-5 or Qwen 3.6 Max (preview)?

Qwen 3.6 Max (preview) has the edge for agentic tasks in this comparison, averaging 65.4 versus 56.2. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 17, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.