Enter opens the highlighted result. Esc closes.

GLM 4.6 vs Phi 4

GLM 4.6 leads Phi 4 on the Artificial Analysis Intelligence Index, 18.5 to 5.9, and Phi 4 costs 15.7x less per output token ($0.14 vs $2.20 per million). Updated October 21, 2026; 38 benchmarks have a result for both.

Replace GLM 4.6 Replace Phi 4
GLM 4.6Z.ai
Coding
8.8
Overall
18.5
Output $/M
$2.20
38
Phi 4Microsoft
Coding
No data
Overall
5.9
Output $/M
$0.14
0
vs boards won of 38 shared

GLM 4.6 or Phi 4: which to pick

Only GLM 4.6 has a coding score, 8.8 on the Vibe Coding Index; Phi 4 has none, so the two cannot be ranked on coding.

Pick Phi 4 for output tokens 15.7x cheaper ($0.14 vs $2.20 per million).

Model AGLM 4.6Z.ai8.8/1002 independent benchmarksNo cost per solved taskModel BPhi 4MicrosoftNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
38
GLM 4.6 only
28
Phi 4 only
7
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 4.6 8.8 from 2 benchmarks, Phi 4 not benchmarked.
Widest category
Agentic work, 76.9 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: GLM 4.6 76.9% against Phi 4 0.0%, 76.9 points apart on a 0 to 100 scale.
Output price
GLM 4.6 $2.20 against Phi 4 $0.14 per million output tokens, 15.7x apart.
Context window
GLM 4.6 takes 205K tokens, Phi 4 16K.

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 4.6BarsPhi 4Ties
Coding40
Intelligence10
Agentic work10
Reasoning50
Math40
Knowledge50
General180
All shared boards380
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
Coding benchmarks for GLM 4.6 and Phi 4
BenchmarkGLM 4.6Phi 4Leader
SWE-bench Verified68.2%Not measuredOnly GLM 4.6 measured
LMArena WebDev1341Not measuredOnly GLM 4.6 measured
AA Coding Index45.8Not measuredOnly GLM 4.6 measured
LiveCodeBench (Vals AI)81.0%Not measuredOnly GLM 4.6 measured
Vibe Code Bench (Vals AI)3.1%Not measuredOnly GLM 4.6 measured
LiveCodeBench (Artificial Analysis run)69.5%23.1%GLM 4.6
Terminal-Bench Hard (Artificial Analysis run)28.8%3.8%GLM 4.6
Terminal-Bench24.5%Not measuredOnly GLM 4.6 measured
ALE-Bench340.8Not measuredOnly GLM 4.6 measured
LMArena Text: coding14491231GLM 4.6
LMArena Text: software and IT14551228GLM 4.6
LMArena WebDev: HTML1350Not measuredOnly GLM 4.6 measured
Neither model has a result on the other 26 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GLM 4.6 and Phi 4
BenchmarkGLM 4.6Phi 4Leader
AA Intelligence Index18.55.9GLM 4.6
Epoch Capabilities IndexNot measured130.5Only Phi 4 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GLM 4.6 and Phi 4
BenchmarkGLM 4.6Phi 4Leader
Design Arena: agents building full-stack apps1029Not measuredOnly GLM 4.6 measured
Design Arena: agents building mobile apps1096Not measuredOnly GLM 4.6 measured
Design Arena: agents building Android apps1084Not measuredOnly GLM 4.6 measured
Design Arena: agents building Godot games1180Not measuredOnly GLM 4.6 measured
τ²-Bench Telecom76.9%0.0%GLM 4.6
BALROGNot measured11.6%Only Phi 4 measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for GLM 4.6 and Phi 4
BenchmarkGLM 4.6Phi 4Leader
GPQA Diamond74.5%Not measuredOnly GLM 4.6 measured
GPQA Diamond (Artificial Analysis run)78.0%57.5%GLM 4.6
Humanity's Last Exam (Artificial Analysis run)14.5%3.8%GLM 4.6
GPQA Diamond (Epoch AI run)Not measured56.1%Only Phi 4 measured
LMArena Text: hard prompts14401220GLM 4.6
LMArena Text: expert14321203GLM 4.6
LMArena Text: hard prompts in English14451230GLM 4.6
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for GLM 4.6 and Phi 4
BenchmarkGLM 4.6Phi 4Leader
AIME92.7%Not measuredOnly GLM 4.6 measured
MGSM (Vals AI)89.8%Not measuredOnly GLM 4.6 measured
AA Math Index86.018.0GLM 4.6
AIME 2025 (Artificial Analysis run)86.0%18.0%GLM 4.6
OTIS Mock AIMENot measured13.8%Only Phi 4 measured
MATH level 5Not measured64.9%Only Phi 4 measured
LMArena Text: math14321246GLM 4.6
LMArena Text: mathematical work14471254GLM 4.6
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for GLM 4.6 and Phi 4
BenchmarkGLM 4.6Phi 4Leader
MMLU Pro82.2%Not measuredOnly GLM 4.6 measured
LegalBench (Vals AI)79.6%Not measuredOnly GLM 4.6 measured
CorpFin (Vals AI)56.8%Not measuredOnly GLM 4.6 measured
TaxEval (Vals AI)66.2%Not measuredOnly GLM 4.6 measured
MedQA (Vals AI)92.2%Not measuredOnly GLM 4.6 measured
MMLU Pro (Artificial Analysis run)82.9%71.4%GLM 4.6
MMLUNot measured84.8%Only Phi 4 measured
LMArena Text: science14561206GLM 4.6
LMArena Text: medicine and healthcare14551202GLM 4.6
LMArena Text: legal and government14481241GLM 4.6
LMArena Text: business and finance14161199GLM 4.6
Neither model has a result on the other 6 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for GLM 4.6 and Phi 4
BenchmarkGLM 4.6Phi 4Leader
Design Arena: websites1174Not measuredOnly GLM 4.6 measured
Design Arena: UI components1148Not measuredOnly GLM 4.6 measured
Design Arena: game dev1151Not measuredOnly GLM 4.6 measured
Design Arena: data viz1161Not measuredOnly GLM 4.6 measured
Design Arena: 3D1129Not measuredOnly GLM 4.6 measured
Design Arena: all code categories1166Not measuredOnly GLM 4.6 measured
Design Arena: SVG1109Not measuredOnly GLM 4.6 measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index180
General benchmarks for GLM 4.6 and Phi 4
BenchmarkGLM 4.6Phi 4Leader
IFBench43.4%23.5%GLM 4.6
Long context reasoning (AA-LCR)54.0%0.0%GLM 4.6
Creative writing (Lech Mazur)Not measured62.6%Only Phi 4 measured
LMArena Text14401217GLM 4.6
LMArena Text: instruction following14101201GLM 4.6
LMArena Text: creative writing14121181GLM 4.6
LMArena Text: English14491231GLM 4.6
LMArena Text: non-English14261197GLM 4.6
LMArena Text: Chinese14991212GLM 4.6
LMArena Text: German14471222GLM 4.6
LMArena Text: Japanese13931158GLM 4.6
LMArena Text: Korean14001151GLM 4.6
LMArena Text: French14591224GLM 4.6
LMArena Text: Spanish14361234GLM 4.6
LMArena Text: Russian14181209GLM 4.6
LMArena Text: Polish1447Not measuredOnly GLM 4.6 measured
LMArena Text: multi-turn14271206GLM 4.6
LMArena Text: longer queries14221217GLM 4.6
LMArena Text: writing and language14151198GLM 4.6
LMArena Text: entertainment and media14091162GLM 4.6
Neither model has a result on the other 26 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 4.6 and Phi 4
BenchmarkGLM 4.6Phi 4Leader
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 4.6$0.0017Fits in one request
Phi 4$0.0001Fits in one request

Phi 4 costs less

Repository review

50K input + 3K output tokens

GLM 4.6$0.037Fits in one request
Phi 4$0.0039Exceeds the context window

Phi 4 costs less

Agent loop

200K input + 10K output tokens

GLM 4.6$0.142Exceeds the context window
Phi 4$0.015Exceeds the context window

Phi 4 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 4.6 and Phi 4
SpecificationZ.ai GLM 4.6Microsoft Phi 4
MakerZ.aiMicrosoft
WeightsOpen weightsOpen weights
ReleasedSeptember 30, 2025January 10, 2025
Context window205K16K
Input $/Mtok$0.60$0.07
Output $/Mtok$2.20$0.14
Coding index8.8Not benchmarked
Independent measurements behind it20
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 4.6 better than Phi 4 for coding?

Only GLM 4.6 has a coding score, 8.8 on the Vibe Coding Index; Phi 4 has none, so the two cannot be ranked on coding. Pick Phi 4 for output tokens 15.7x cheaper ($0.14 vs $2.20 per million).

Which is cheaper, GLM 4.6 or Phi 4?

GLM 4.6 costs $0.60 per million input tokens and $2.20 per million output tokens; Phi 4 costs $0.07 and $0.14. Cost per solved task is known for neither of them.

Which has the bigger context window, GLM 4.6 or Phi 4?

GLM 4.6, with 205K tokens against 16K.

How many benchmarks is the GLM 4.6 vs Phi 4 comparison based on?

38 benchmarks have a result for both models as of October 21, 2026. GLM 4.6's coding index rests on 2 independent benchmarks and Phi 4's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next