Enter opens the highlighted result. Esc closes.

GLM 4.7 Flash vs Qwen2.5 72B Instruct

GLM 4.7 Flash leads Qwen2.5 72B Instruct on the Artificial Analysis Intelligence Index, 14.9 to 7.7, at about the same output price ($0.40 vs $0.40 per million). Updated October 22, 2026; 34 benchmarks have a result for both.

Replace GLM 4.7 Flash Replace Qwen2.5 72B Instruct
GLM 4.7 FlashZ.ai
Coding
No data
Overall
42.1
Output $/M
$0.40
34
Qwen2.5 72B InstructQwen
Coding
No data
Overall
26.5
Output $/M
$0.40
0
vs boards won of 34 shared

GLM 4.7 Flash or Qwen2.5 72B Instruct: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick GLM 4.7 Flash for a larger context window (200K against 33K tokens).

Model AGLM 4.7 FlashZ.aiNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen2.5 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
34
GLM 4.7 Flash only
9
Qwen2.5 72B Instruct only
19
Like-for-like categories
7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

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 4.7 Flash not benchmarked, Qwen2.5 72B Instruct not benchmarked.
Widest category
Agentic work, 64.3 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: GLM 4.7 Flash 98.8% against Qwen2.5 72B Instruct 34.5%, 64.3 points apart on a 0 to 100 scale.
Output price
Both cost $0.40 per million output tokens.
Context window
GLM 4.7 Flash takes 200K tokens, Qwen2.5 72B Instruct 33K.

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 4.7 FlashBarsQwen2.5 72B InstructTies
Coding30
Intelligence10
Agentic work10
Reasoning60
Math30
Knowledge40
General160
All shared boards340
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for GLM 4.7 Flash and Qwen2.5 72B Instruct
BenchmarkGLM 4.7 FlashQwen2.5 72B InstructLeader
LiveCodeBench (Artificial Analysis run)Not measured27.6%Only Qwen2.5 72B Instruct measured
Terminal-Bench Hard (Artificial Analysis run)22.0%4.5%GLM 4.7 Flash
WeirdMLNot measured16.0%Only Qwen2.5 72B Instruct measured
LMArena Text: coding13821292GLM 4.7 Flash
LMArena Text: software and IT13891292GLM 4.7 Flash
Neither model has a result on the other 34 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GLM 4.7 Flash and Qwen2.5 72B Instruct
BenchmarkGLM 4.7 FlashQwen2.5 72B InstructLeader
AA Intelligence Index14.97.7GLM 4.7 Flash
Epoch Capabilities IndexNot measured129.0Only Qwen2.5 72B Instruct measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GLM 4.7 Flash and Qwen2.5 72B Instruct
BenchmarkGLM 4.7 FlashQwen2.5 72B InstructLeader
τ²-Bench Telecom98.8%34.5%GLM 4.7 Flash
METR time horizonsNot measured35.8%Only Qwen2.5 72B Instruct measured
BALROGNot measured16.2%Only Qwen2.5 72B Instruct measured
TheAgentCompanyNot measured5.7%Only Qwen2.5 72B Instruct measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
Reasoning benchmarks for GLM 4.7 Flash and Qwen2.5 72B Instruct
BenchmarkGLM 4.7 FlashQwen2.5 72B InstructLeader
GPQA Diamond (Artificial Analysis run)58.1%49.1%GLM 4.7 Flash
Humanity's Last Exam (Artificial Analysis run)7.6%3.6%GLM 4.7 Flash
GPQA Diamond (Epoch AI run)60.5%49.1%GLM 4.7 Flash
BIG-Bench HardNot measured79.8%Only Qwen2.5 72B Instruct measured
LMArena Text: hard prompts13561271GLM 4.7 Flash
LMArena Text: expert13571245GLM 4.7 Flash
LMArena Text: hard prompts in English13691279GLM 4.7 Flash
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for GLM 4.7 Flash and Qwen2.5 72B Instruct
BenchmarkGLM 4.7 FlashQwen2.5 72B InstructLeader
AA Math IndexNot measured14.0Only Qwen2.5 72B Instruct measured
AIME 2025 (Artificial Analysis run)Not measured14.0%Only Qwen2.5 72B Instruct measured
OTIS Mock AIME58.3%8.1%GLM 4.7 Flash
MATH level 5Not measured63.2%Only Qwen2.5 72B Instruct measured
LMArena Text: math13551283GLM 4.7 Flash
LMArena Text: mathematical work13691290GLM 4.7 Flash
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for GLM 4.7 Flash and Qwen2.5 72B Instruct
BenchmarkGLM 4.7 FlashQwen2.5 72B InstructLeader
MMLU Pro (Artificial Analysis run)Not measured72.0%Only Qwen2.5 72B Instruct measured
MMLUNot measured85.3%Only Qwen2.5 72B Instruct measured
AI2 Reasoning ChallengeNot measured94.5%Only Qwen2.5 72B Instruct measured
LMArena Text: science13581275GLM 4.7 Flash
LMArena Text: medicine and healthcare13431258GLM 4.7 Flash
LMArena Text: legal and government13571288GLM 4.7 Flash
LMArena Text: business and finance13431253GLM 4.7 Flash
Neither model has a result on the other 11 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for GLM 4.7 Flash and Qwen2.5 72B Instruct
BenchmarkGLM 4.7 FlashQwen2.5 72B InstructLeader
Design Arena: websites1194Not measuredOnly GLM 4.7 Flash measured
Design Arena: UI components1205Not measuredOnly GLM 4.7 Flash measured
Design Arena: game dev1134Not measuredOnly GLM 4.7 Flash measured
Design Arena: data viz1123Not measuredOnly GLM 4.7 Flash measured
Design Arena: 3D1120Not measuredOnly GLM 4.7 Flash measured
Design Arena: all code categories1177Not measuredOnly GLM 4.7 Flash measured
Design Arena: SVG1037Not measuredOnly GLM 4.7 Flash measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index160
General benchmarks for GLM 4.7 Flash and Qwen2.5 72B Instruct
BenchmarkGLM 4.7 FlashQwen2.5 72B InstructLeader
IFBench60.8%36.9%GLM 4.7 Flash
Long context reasoning (AA-LCR)41.7%Not measuredOnly GLM 4.7 Flash measured
DTBenchNot measured62.9%Only Qwen2.5 72B Instruct measured
LMCANot measured13.4%Only Qwen2.5 72B Instruct measured
HellaSwagNot measured84.8%Only Qwen2.5 72B Instruct measured
WinoGrandeNot measured82.3%Only Qwen2.5 72B Instruct measured
PIQANot measured82.6%Only Qwen2.5 72B Instruct measured
LMArena Text13511269GLM 4.7 Flash
LMArena Text: instruction following13271254GLM 4.7 Flash
LMArena Text: creative writing12961221GLM 4.7 Flash
LMArena Text: English13731283GLM 4.7 Flash
LMArena Text: non-English13301252GLM 4.7 Flash
LMArena Text: Chinese14031273GLM 4.7 Flash
LMArena Text: German13361234GLM 4.7 Flash
LMArena Text: JapaneseNot measured1180Only Qwen2.5 72B Instruct measured
LMArena Text: Korean12831188GLM 4.7 Flash
LMArena Text: French13321280GLM 4.7 Flash
LMArena Text: Spanish13501255GLM 4.7 Flash
LMArena Text: Russian13331264GLM 4.7 Flash
LMArena Text: Polish1291Not measuredOnly GLM 4.7 Flash measured
LMArena Text: multi-turn13421272GLM 4.7 Flash
LMArena Text: longer queries13451281GLM 4.7 Flash
LMArena Text: writing and language13201247GLM 4.7 Flash
LMArena Text: entertainment and media13041211GLM 4.7 Flash
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 4.7 Flash and Qwen2.5 72B Instruct
BenchmarkGLM 4.7 FlashQwen2.5 72B InstructLeader
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 4.7 Flash$0.0003Fits in one request
Qwen2.5 72B Instruct$0.0006Fits in one request

GLM 4.7 Flash costs less

Repository review

50K input + 3K output tokens

GLM 4.7 Flash$0.0045Fits in one request
Qwen2.5 72B Instruct$0.019Exceeds the context window

GLM 4.7 Flash costs less

Agent loop

200K input + 10K output tokens

GLM 4.7 Flash$0.017Exceeds the context window
Qwen2.5 72B Instruct$0.076Exceeds the context window

GLM 4.7 Flash 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 4.7 Flash and Qwen2.5 72B Instruct
SpecificationZ.ai GLM 4.7 FlashQwen2.5 72B Instruct
MakerZ.aiQwen
WeightsOpen weightsOpen weights
ReleasedJanuary 19, 2026September 19, 2024
Context window200K33K
Input $/Mtok$0.0653$0.36
Output $/Mtok$0.40$0.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 4.7 Flash better than Qwen2.5 72B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GLM 4.7 Flash for a larger context window (200K against 33K tokens).

Which is cheaper, GLM 4.7 Flash or Qwen2.5 72B Instruct?

GLM 4.7 Flash costs $0.0653 per million input tokens and $0.40 per million output tokens; Qwen2.5 72B Instruct costs $0.36 and $0.40. Cost per solved task is known for neither of them.

Which has the bigger context window, GLM 4.7 Flash or Qwen2.5 72B Instruct?

GLM 4.7 Flash, with 200K tokens against 33K.

How many benchmarks is the GLM 4.7 Flash vs Qwen2.5 72B Instruct comparison based on?

34 benchmarks have a result for both models as of October 22, 2026. GLM 4.7 Flash's coding index rests on 0 independent benchmarks and Qwen2.5 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next