LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GLM 5.1 vs Qwen3.7 Max

Updated October 21, 2026. 52 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GLM 5.1 Replace Qwen3.7 Max
GLM 5.1Z.ai
Coding
44.0
Overall
26.1
Output $/M
$4.40
16
Qwen3.7 MaxQwen
Coding
45.1
Overall
29.5
Output $/M
$4.425
35
vs boards won of 52 shared, 1 tied

Decision reading

GLM 5.1 and Qwen3.7 Max are level for coding, 44.0 against 45.1 on the Vibe Coding Index, so price and context decide.

Pick GLM 5.1 when output tokens cost 1.0x less, or when a solved task costs $0.60 against $4.69. Pick Qwen3.7 Max when the context window is larger, 1M against 205K tokens, or when what matters is LMArena WebDev or AA Coding Index, where it leads.

Model AGLM 5.1Z.ai44.0/1001 independent benchmark$0.60 per solved taskModel BQwen3.7 MaxQwen45.1/1001 independent benchmark$4.69 per solved task
Shared results
52
GLM 5.1 only
37
Qwen3.7 Max only
7
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
GLM 5.1 44.0 from 1 benchmark, Qwen3.7 Max 45.1 from 1 benchmark.
Widest category
Math, 11.2 points apart on average over 3 shared benchmarks.
Widest single gap
FrontierMath, tiers 1 to 3: GLM 5.1 36.8% against Qwen3.7 Max 64.6%, 27.7 points apart on a 0 to 100 scale.
Output price
GLM 5.1 $4.40 against Qwen3.7 Max $4.425 per million output tokens, 1.0x apart.
Context window
GLM 5.1 takes 205K tokens, Qwen3.7 Max 1M.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryGLM 5.1BarsQwen3.7 MaxTies
Coding210
Intelligence02
Agentic work75
Reasoning06
Math03
Knowledge24
Web design521 tie
General03
All shared boards16351 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index210
Coding benchmarks for GLM 5.1 and Qwen3.7 Max
BenchmarkGLM 5.1Qwen3.7 MaxLeader
LMArena WebDev15081515Qwen3.7 Max
AA Coding Index55.866.0Qwen3.7 Max
LiveCodeBench (Vals AI)81.4%87.1%Qwen3.7 Max
SWE-bench Verified (Vals AI)76.4%68.8%GLM 5.1
Vibe Code Bench (Vals AI)31.5%47.7%Qwen3.7 Max
Code migration (Vals AI)25.8%13.1%GLM 5.1
ProgramBench (Vals AI)0.0%Not measuredOnly GLM 5.1 measured
Terminal-Bench 2.1 (Vals AI)56.9%61.0%Qwen3.7 Max
SciCode44.8%49.5%Qwen3.7 Max
Terminal-Bench Hard (Artificial Analysis run)43.2%50.8%Qwen3.7 Max
WeirdML57.1%Not measuredOnly GLM 5.1 measured
ALE-Bench887.11189.4Qwen3.7 Max
LMArena Text: coding1485Not measuredOnly GLM 5.1 measured
LMArena Text: software and IT1484Not measuredOnly GLM 5.1 measured
LMArena WebDev: React15051514Qwen3.7 Max
LMArena WebDev: HTML15081512Qwen3.7 Max
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GLM 5.1 and Qwen3.7 Max
BenchmarkGLM 5.1Qwen3.7 MaxLeader
AA Intelligence Index26.129.5Qwen3.7 Max
Epoch Capabilities Index149.8154.0Qwen3.7 Max
Agentic workLike-for-likePublic boards, shown as published, kept out of the index75
Agentic work benchmarks for GLM 5.1 and Qwen3.7 Max
BenchmarkGLM 5.1Qwen3.7 MaxLeader
AA Agentic Index23.922.5GLM 5.1
Design Arena: agents building web apps11751208Qwen3.7 Max
Design Arena: agents building full-stack apps11671191Qwen3.7 Max
Design Arena: agents building mobile apps11621153GLM 5.1
Design Arena: agents building Android apps11861165GLM 5.1
Design Arena: agents building Godot games10531187Qwen3.7 Max
Design Arena: agents building games11641161GLM 5.1
Design Arena: HTML slides11701158GLM 5.1
Design Arena: PowerPoint slides11891196Qwen3.7 Max
Design Arena: spreadsheets1315Not measuredOnly GLM 5.1 measured
Finance Agent (Vals AI)44.8%47.8%Qwen3.7 Max
Tax Agent Bench (Vals AI)Not measured15.8%Only Qwen3.7 Max measured
Legal Research Bench (Vals AI)27.9%25.5%GLM 5.1
Excel Modeling Benchmark (Vals AI)Not measured57.0%Only Qwen3.7 Max measured
τ²-Bench Telecom97.7%94.7%GLM 5.1
APEX-Agents40.9%Not measuredOnly GLM 5.1 measured
Vending-Bench 2$5,634Not measuredOnly GLM 5.1 measured
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
Reasoning benchmarks for GLM 5.1 and Qwen3.7 Max
BenchmarkGLM 5.1Qwen3.7 MaxLeader
GPQA Diamond84.5%90.2%Qwen3.7 Max
GPQA Diamond (Artificial Analysis run)86.8%92.3%Qwen3.7 Max
Humanity's Last Exam (Artificial Analysis run)30.1%40.5%Qwen3.7 Max
GPQA Diamond (Epoch AI run)89.9%90.9%Qwen3.7 Max
SimpleBench55.1%70.4%Qwen3.7 Max
Chess puzzles20.0%26.0%Qwen3.7 Max
Mystery game puzzlesNot measured32.0%Only Qwen3.7 Max measured
EBR-benchNot measured9.5%Only Qwen3.7 Max measured
LMArena Text: hard prompts1473Not measuredOnly GLM 5.1 measured
LMArena Text: expert1478Not measuredOnly GLM 5.1 measured
LMArena Text: hard prompts in English1482Not measuredOnly GLM 5.1 measured
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for GLM 5.1 and Qwen3.7 Max
BenchmarkGLM 5.1Qwen3.7 MaxLeader
AIME91.9%Not measuredOnly GLM 5.1 measured
OTIS Mock AIME93.3%95.6%Qwen3.7 Max
FrontierMath, tiers 1 to 336.8%64.6%Qwen3.7 Max
FrontierMath, tier 4Not measured34.1%Only Qwen3.7 Max measured
ProofBench22.2%26.0%Qwen3.7 Max
LMArena Text: math1473Not measuredOnly GLM 5.1 measured
LMArena Text: mathematical work1470Not measuredOnly GLM 5.1 measured
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index24
Knowledge benchmarks for GLM 5.1 and Qwen3.7 Max
BenchmarkGLM 5.1Qwen3.7 MaxLeader
MMLU Pro86.9%89.3%Qwen3.7 Max
LegalBench (Vals AI)84.4%84.9%Qwen3.7 Max
CaseLaw (Vals AI)51.5%Not measuredOnly GLM 5.1 measured
CorpFin (Vals AI)64.5%63.7%GLM 5.1
TaxEval (Vals AI)71.2%75.3%Qwen3.7 Max
MedCode (Vals AI)41.6%38.8%GLM 5.1
SimpleQA Verified34.0%55.8%Qwen3.7 Max
LMArena Text: science1478Not measuredOnly GLM 5.1 measured
LMArena Text: medicine and healthcare1474Not measuredOnly GLM 5.1 measured
LMArena Text: legal and government1465Not measuredOnly GLM 5.1 measured
LMArena Text: business and finance1452Not measuredOnly GLM 5.1 measured
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index52
Web design benchmarks for GLM 5.1 and Qwen3.7 Max
BenchmarkGLM 5.1Qwen3.7 MaxLeader
Design Arena: websites12901274GLM 5.1
Design Arena: UI components12921269GLM 5.1
Design Arena: game dev12651265Tie
Design Arena: data viz13661275GLM 5.1
Design Arena: 3D13361266GLM 5.1
Design Arena: all code categories12681275Qwen3.7 Max
Design Arena: SVG12171216GLM 5.1
Design Arena: ASCII art11421211Qwen3.7 Max
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index03
General benchmarks for GLM 5.1 and Qwen3.7 Max
BenchmarkGLM 5.1Qwen3.7 MaxLeader
Public Benefits Bench (Vals AI)61.8%Not measuredOnly GLM 5.1 measured
MedScribe (Vals AI)72.3%79.4%Qwen3.7 Max
IFBench76.3%80.5%Qwen3.7 Max
Long context reasoning (AA-LCR)73.7%79.0%Qwen3.7 Max
DTBenchNot measured92.3%Only Qwen3.7 Max measured
LMCANot measured44.0%Only Qwen3.7 Max measured
ExploitBench18.1%Not measuredOnly GLM 5.1 measured
LMArena Text1463Not measuredOnly GLM 5.1 measured
LMArena Text: instruction following1453Not measuredOnly GLM 5.1 measured
LMArena Text: creative writing1453Not measuredOnly GLM 5.1 measured
LMArena Text: English1476Not measuredOnly GLM 5.1 measured
LMArena Text: non-English1448Not measuredOnly GLM 5.1 measured
LMArena Text: Chinese1515Not measuredOnly GLM 5.1 measured
LMArena Text: German1467Not measuredOnly GLM 5.1 measured
LMArena Text: Japanese1435Not measuredOnly GLM 5.1 measured
LMArena Text: Korean1424Not measuredOnly GLM 5.1 measured
LMArena Text: French1470Not measuredOnly GLM 5.1 measured
LMArena Text: Spanish1468Not measuredOnly GLM 5.1 measured
LMArena Text: Russian1454Not measuredOnly GLM 5.1 measured
LMArena Text: Polish1449Not measuredOnly GLM 5.1 measured
LMArena Text: multi-turn1473Not measuredOnly GLM 5.1 measured
LMArena Text: longer queries1467Not measuredOnly GLM 5.1 measured
LMArena Text: writing and language1454Not measuredOnly GLM 5.1 measured
LMArena Text: entertainment and media1442Not measuredOnly GLM 5.1 measured
Neither model has a result on the other 22 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 5.1 and Qwen3.7 Max
BenchmarkGLM 5.1Qwen3.7 MaxLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

GLM 5.1$0.0036Fits in one request
Qwen3.7 Max$0.0037Fits in one request

GLM 5.1 costs less

Repository review

50K input + 3K output tokens

GLM 5.1$0.083Fits in one request
Qwen3.7 Max$0.087Fits in one request

GLM 5.1 costs less

Agent loop

200K input + 10K output tokens

GLM 5.1$0.324Exceeds the context window
Qwen3.7 Max$0.339Fits in one request

GLM 5.1 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of GLM 5.1 and Qwen3.7 Max
SpecificationZ.ai GLM 5.1Qwen3.7 Max
MakerZ.aiQwen
WeightsOpen weightsNo public weights listed
ReleasedApril 7, 2026May 21, 2026
Context window205K1M
Input $/Mtok$1.40$1.475
Output $/Mtok$4.40$4.425
Coding index44.045.1
Independent measurements behind it11
Cost per solved task$0.60$4.69
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 5.1 better than Qwen3.7 Max for coding?

GLM 5.1 and Qwen3.7 Max are level for coding, 44.0 against 45.1 on the Vibe Coding Index, so price and context decide. Pick GLM 5.1 when output tokens cost 1.0x less, or when a solved task costs $0.60 against $4.69. Pick Qwen3.7 Max when the context window is larger, 1M against 205K tokens, or when what matters is LMArena WebDev or AA Coding Index, where it leads.

Which is cheaper, GLM 5.1 or Qwen3.7 Max?

GLM 5.1 costs $1.40 per million input tokens and $4.40 per million output tokens; Qwen3.7 Max costs $1.475 and $4.425. Per solved SWE-bench Verified task, GLM 5.1 costs $0.60 and Qwen3.7 Max $4.69.

Which has the bigger context window, GLM 5.1 or Qwen3.7 Max?

Qwen3.7 Max, with 1M tokens against 205K.

How many benchmarks is the GLM 5.1 vs Qwen3.7 Max comparison based on?

52 benchmarks have a result for both models as of October 21, 2026. GLM 5.1's coding index rests on 1 independent benchmark and Qwen3.7 Max's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next