Skip to main content

Model comparison

GLM-4.7 vs Qwen3.5 397B

Data verified

Head-to-head evidence from 23 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

61.16/100
Margin
4.1pts
← winning
57.01/100
1 category wins3 category wins

Public leaderboard positions: GLM-4.7 #42 (Supported); Qwen3.5 397B #71 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GLM-4.7 and Qwen3.5 397B share 23 comparable benchmark results. 4 of 8 categories are comparable. 7 results are unique to GLM-4.7; 32 to Qwen3.5 397B.

Updated July 22, 2026
Shared results
23
GLM-4.7 only
7
Qwen3.5 397B only
32
Comparable categories
4 / 8

Pick GLM-4.7 if you want the stronger benchmark profile. Qwen3.5 397B only becomes the better choice if mathematics is the priority or you would rather avoid the extra latency and token burn of a reasoning model.

Confidence note. This is a partial-evidence comparison with 23 shared benchmark results across 5 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-4.7 is clearly ahead on the BenchAlign aggregate, 61.16 to 57.01. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GLM-4.7's sharpest advantage is in coding, where it averages 75.4 against 66.5. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 41% to 52.5%. Qwen3.5 397B does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.

Qwen3.5 397B is also the more expensive model on tokens at $0.60 input / $3.60 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for GLM-4.7. That is roughly Infinityx on output cost alone. GLM-4.7 is the reasoning model in the pair, while Qwen3.5 397B 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-4.7 gives you the larger context window at 200K, compared with 128K for Qwen3.5 397B.

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-4.7 and Qwen3.5 397B
CategoryGLM-4.7ΔQwen3.5 397B
MathGLM-4.71.8Margin 88.8Qwen3.5 397B90.6
AgenticGLM-4.745.7Margin 10.8Qwen3.5 397B56.5
CodingGLM-4.775.4Margin 8.9Qwen3.5 397B66.5
KnowledgeGLM-4.751.8Margin 4.8Qwen3.5 397B56.6
ReasoningGLM-4.7Not measuredMarginNo overlapQwen3.5 397B63.2
MultilingualGLM-4.7Not measuredMarginNo overlapQwen3.5 397B84.7
MultimodalGLM-4.7Not measuredMarginNo overlapQwen3.5 397B79.6
Inst. FollowingGLM-4.7Not measuredMarginNo overlapQwen3.5 397B92.6

Decisive benchmark drivers

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

More
A · GLM-4.7B · Qwen3.5 397B
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 41%B 52.5%
    Winner: Qwen3.5 397BΔ 11.5
    Terminal-Bench 2.0: GLM-4.7 scored 41%; Qwen3.5 397B scored 52.5%. Qwen3.5 397B wins this benchmark.
  2. BrowseComp

    Agentic
    Source ↗
    A 52%B 62%
    Winner: Qwen3.5 397BΔ 10
    BrowseComp: GLM-4.7 scored 52%; Qwen3.5 397B scored 62%. Qwen3.5 397B wins this benchmark.
  3. HLE

    Knowledge
    Source ↗
    A 24.8%B 28.7%
    Winner: Qwen3.5 397BΔ 3.9
    HLE: GLM-4.7 scored 24.8%; Qwen3.5 397B scored 28.7%. Qwen3.5 397B wins this benchmark.
  4. MMLU-Pro

    Knowledge
    Source ↗
    A 84.3%B 87.8%
    Winner: Qwen3.5 397BΔ 3.5
    MMLU-Pro: GLM-4.7 scored 84.3%; Qwen3.5 397B scored 87.8%. Qwen3.5 397B wins this benchmark.
  5. GPQA

    Knowledge
    Source ↗
    A 85.7%B 88.4%
    Winner: Qwen3.5 397BΔ 2.7
    GPQA: GLM-4.7 scored 85.7%; Qwen3.5 397B scored 88.4%. Qwen3.5 397B wins this benchmark.

Operational comparison

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

MetricGLM-4.7Qwen3.5 397BComparison
Input / output priceUSD per 1M tokensGLM-4.7$0 input / $0 outputQwen3.5 397B$0.6 input / $3.6 outputGLM-4.7 has the lower combined listed price.
Generation speedtokens per secondGLM-4.782 tok/sQwen3.5 397B96 tok/sQwen3.5 397B has the higher measured throughput.
First-answer latencyseconds to first tokenGLM-4.71.10 sQwen3.5 397B2.44 sGLM-4.7 reaches the first token sooner.
Context windowmaximum listed tokensGLM-4.7200KQwen3.5 397B128KGLM-4.7 lists the larger context window.

Benchmark Deep Dive

AgenticQwen3.5 397B wins
BenchmarkGLM-4.7Qwen3.5 397BResult
Terminal-Bench 2.0Source 41%52.5%Qwen3.5 397B leads
BrowseCompSource 52%62%Qwen3.5 397B leads
VITA-BenchSource 15.5%43.7%Qwen3.5 397B leads
AA Agentic IndexSource 25.4%19.9%GLM-4.7 leads
τ²-bench resultsSource 95.9%95.6%GLM-4.7 leads
Gert LabsSource 39.95%46.76%Qwen3.5 397B leads
GDPval-AASource 33.3%23.1%GLM-4.7 leads
GDPval-AASource 1165962GLM-4.7 leads
Claw-EvalSource 56.8%Not comparable
QwenClawBenchSource 51.8%Not comparable
τ³-bench resultsSource 68.4%Not comparable
DeepPlanningSource 37.6%Not comparable
ToolathlonSource 36.3%Not comparable
MCP AtlasSource 46.1%Not comparable
MCP-TasksSource 74.2%Not comparable
WideResearchSource 74.0%Not comparable
ResearchClawBenchSource 14.2%Not comparable
APEX-Agents-AASource 15.3%Not comparable
CodingGLM-4.7 wins
BenchmarkGLM-4.7Qwen3.5 397BResult
SWE-bench VerifiedSource 73.8%76.2%Qwen3.5 397B leads
LiveCodeBenchSource 84.9%Not comparable
SWE-RebenchSource 58.7%Not comparable
AA Coding IndexSource 45.3%48.2%Qwen3.5 397B leads
AA-SciCodeSource 45.1%42.0%GLM-4.7 leads
AA LiveCodeBenchSource 89.4%Not comparable
LiveCodeBench v6Source 83.6%Not comparable
SWE-bench ProSource 50.9%Not comparable
Reasoning
BenchmarkGLM-4.7Qwen3.5 397BResult
AA-LCRSource 64.0%65.7%Qwen3.5 397B leads
CritPtSource 1.7%1.7%Tie
LongBench v2Source 63.2%Not comparable
AI-NeedleSource 68.7%Not comparable
KnowledgeQwen3.5 397B wins
BenchmarkGLM-4.7Qwen3.5 397BResult
GPQASource 85.7%88.4%Qwen3.5 397B leads
MMLU-ProSource 84.3%87.8%Qwen3.5 397B leads
HLESource 24.8%28.7%Qwen3.5 397B leads
Artificial Analysis Intelligence IndexSource 33.7%33.7%GLM-4.7 leads
AA-GPQA DiamondSource 85.9%89.3%Qwen3.5 397B leads
AA-HLESource 25.1%27.3%Qwen3.5 397B leads
AA-Omniscience IndexSource -34.6%-29.8%Qwen3.5 397B leads
AA-Omniscience AccuracySource 29.3%31.4%Qwen3.5 397B leads
AA-Omniscience Hallucination RateSource 90.3%89.1%Qwen3.5 397B leads
SuperGPQASource 70.4%Not comparable
MMLU-ReduxSource 94.9%Not comparable
C-EvalSource 93%Not comparable
MathQwen3.5 397B wins
BenchmarkGLM-4.7Qwen3.5 397BResult
AIME 2025Source 95.7%Not comparable
FrontierMath v2 (Tiers 1-3)Source 2.439%Not comparable
FrontierMath v2 (Tier 4)Source 0.000%Not comparable
AIME26Source 93.3%Not comparable
HMMT Feb 2025Source 94.8%Not comparable
HMMT Nov 2025Source 92.7%Not comparable
HMMT Feb 2026Source 87.9%Not comparable
MMAnswerBenchSource 80.9%Not comparable
Multilingual
BenchmarkGLM-4.7Qwen3.5 397BResult
MMLU-ProXSource 84.7%Not comparable
NOVA-63Source 59.1%Not comparable
Multimodal
BenchmarkGLM-4.7Qwen3.5 397BResult
Design Arena WebsiteSource 1255Not comparable
MMMU-ProSource 79%Not comparable
MathVisionSource 88.6%Not comparable
CharXivSource 80.8%Not comparable
VideoMMMUSource 84.7%Not comparable
ScreenSpot ProSource 65.6%Not comparable
V*Source 95.8%Not comparable
AA-MMMU-ProSource 77.3%Not comparable
Inst. Following
BenchmarkGLM-4.7Qwen3.5 397BResult
AA-IFBenchSource 67.9%78.8%Qwen3.5 397B leads
IFEvalSource 92.6%Not comparable
Frequently Asked Questions (5)

Which is better, GLM-4.7 or Qwen3.5 397B?

GLM-4.7 is ahead on BenchLM's BenchAlign leaderboard, 61.16 to 57.01. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 41% and 52.5%.

Which is better for knowledge tasks, GLM-4.7 or Qwen3.5 397B?

Qwen3.5 397B has the edge for knowledge tasks in this comparison, averaging 56.6 versus 51.8. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.

Which is better for coding, GLM-4.7 or Qwen3.5 397B?

GLM-4.7 has the edge for coding in this comparison, averaging 75.4 versus 66.5. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Which is better for math, GLM-4.7 or Qwen3.5 397B?

Qwen3.5 397B has the edge for math in this comparison, averaging 90.6 versus 1.8. GLM-4.7 stays close enough that the answer can still flip depending on your workload.

Which is better for agentic tasks, GLM-4.7 or Qwen3.5 397B?

Qwen3.5 397B has the edge for agentic tasks in this comparison, averaging 56.5 versus 45.7. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 22, 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.