Enter opens the highlighted result. Esc closes.

GLM 4.5 Air vs gpt-oss-20b

GLM 4.5 Air leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 11.1 to 10.0, and gpt-oss-20b costs 7.3x less per output token ($0.15 vs $1.10 per million). Updated October 22, 2026; 41 benchmarks have a result for both.

Replace GLM 4.5 Air Replace gpt-oss-20b
GLM 4.5 AirZ.ai
Coding
No data
Overall
No data
Output $/M
$1.10
34
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
7
vs boards won of 41 shared

GLM 4.5 Air or gpt-oss-20b: which to pick

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

Pick GLM 4.5 Air for work measured by LiveCodeBench (Artificial Analysis run) or τ²-Bench Telecom, where it leads.

Model AGLM 4.5 AirZ.aiNot benchmarkedNo coding benchmarkNo cost per solved taskModel Bgpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
41
GLM 4.5 Air only
7
gpt-oss-20b only
21
Like-for-like categories
8 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 4.5 Air not benchmarked, gpt-oss-20b not benchmarked.
Widest category
Web design, 34.2 points apart on average over 2 shared benchmarks.
Widest single gap
Design Arena: websites: GLM 4.5 Air 1146 against gpt-oss-20b 852, 36.8 points apart on a 0 to 100 scale.
Output price
GLM 4.5 Air $1.10 against gpt-oss-20b $0.15 per million output tokens, 7.3x apart.
Context window
Both take 131K tokens.

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 4.5 AirBarsgpt-oss-20bTies
Coding31
Intelligence10
Agentic work01
Reasoning42
Math22
Knowledge50
Web design20
General171
All shared boards347
CodingLike-for-likeSix of these boards feed the Vibe Coding Index31
Coding benchmarks for GLM 4.5 Air and gpt-oss-20b
BenchmarkGLM 4.5 Airgpt-oss-20bLeader
LiveCodeBench (Vals AI)Not measured80.4%Only gpt-oss-20b measured
LiveCodeBench (Artificial Analysis run)68.4%77.7%gpt-oss-20b
SciCodeNot measured38.9%Only gpt-oss-20b measured
Terminal-Bench Hard (Artificial Analysis run)20.5%10.6%GLM 4.5 Air
Terminal-BenchNot measured3.4%Only gpt-oss-20b measured
GSO-Bench2.9%Not measuredOnly GLM 4.5 Air measured
WeirdMLNot measured40.9%Only gpt-oss-20b measured
ALE-BenchNot measured566.0Only gpt-oss-20b measured
LMArena Text: coding13971307GLM 4.5 Air
LMArena Text: software and IT14011311GLM 4.5 Air
Neither model has a result on the other 29 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GLM 4.5 Air and gpt-oss-20b
BenchmarkGLM 4.5 Airgpt-oss-20bLeader
AA Intelligence Index11.110.0GLM 4.5 Air
Epoch Capabilities IndexNot measured137.7Only gpt-oss-20b measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GLM 4.5 Air and gpt-oss-20b
BenchmarkGLM 4.5 Airgpt-oss-20bLeader
τ²-Bench Telecom46.5%60.2%gpt-oss-20b
BrowseComp-PlusNot measured50.6%Only gpt-oss-20b measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index42
Reasoning benchmarks for GLM 4.5 Air and gpt-oss-20b
BenchmarkGLM 4.5 Airgpt-oss-20bLeader
GPQA DiamondNot measured68.9%Only gpt-oss-20b measured
GPQA Diamond (Artificial Analysis run)73.3%68.8%GLM 4.5 Air
Humanity's Last Exam (Artificial Analysis run)7.0%11.0%gpt-oss-20b
GPQA Diamond (Epoch AI run)Not measured60.8%Only gpt-oss-20b measured
LMArena Text: hard prompts13791274GLM 4.5 Air
LMArena Text: expert13701258GLM 4.5 Air
LMArena Text: hard prompts in English13881292GLM 4.5 Air
Kagi LLM Benchmark43.0%53.2%gpt-oss-20b
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index22
Math benchmarks for GLM 4.5 Air and gpt-oss-20b
BenchmarkGLM 4.5 Airgpt-oss-20bLeader
AIMENot measured86.0%Only gpt-oss-20b measured
MATH 500 (Vals AI)Not measured94.2%Only gpt-oss-20b measured
MGSM (Vals AI)Not measured89.0%Only gpt-oss-20b measured
AA Math Index80.789.3gpt-oss-20b
AIME 2025 (Artificial Analysis run)80.7%89.3%gpt-oss-20b
OTIS Mock AIMENot measured65.3%Only gpt-oss-20b measured
LMArena Text: math13961317GLM 4.5 Air
LMArena Text: mathematical work13961305GLM 4.5 Air
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 4.5 Air and gpt-oss-20b
BenchmarkGLM 4.5 Airgpt-oss-20bLeader
MMLU ProNot measured71.6%Only gpt-oss-20b measured
LegalBench (Vals AI)Not measured70.8%Only gpt-oss-20b measured
CaseLaw (Vals AI)Not measured43.8%Only gpt-oss-20b measured
CorpFin (Vals AI)Not measured53.1%Only gpt-oss-20b measured
TaxEval (Vals AI)Not measured63.7%Only gpt-oss-20b measured
MedQA (Vals AI)Not measured82.9%Only gpt-oss-20b measured
MMLU Pro (Artificial Analysis run)81.5%74.8%GLM 4.5 Air
LMArena Text: science14071296GLM 4.5 Air
LMArena Text: medicine and healthcare14021310GLM 4.5 Air
LMArena Text: legal and government13821280GLM 4.5 Air
LMArena Text: business and finance13711284GLM 4.5 Air
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index20
Web design benchmarks for GLM 4.5 Air and gpt-oss-20b
BenchmarkGLM 4.5 Airgpt-oss-20bLeader
Design Arena: websites1146852GLM 4.5 Air
Design Arena: UI components1120Not measuredOnly GLM 4.5 Air measured
Design Arena: game dev1094Not measuredOnly GLM 4.5 Air measured
Design Arena: data viz1186933GLM 4.5 Air
Design Arena: 3D1122Not measuredOnly GLM 4.5 Air measured
Design Arena: all code categories1137Not measuredOnly GLM 4.5 Air measured
Design Arena: SVG1071Not measuredOnly GLM 4.5 Air measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index171
General benchmarks for GLM 4.5 Air and gpt-oss-20b
BenchmarkGLM 4.5 Airgpt-oss-20bLeader
IFBench37.6%65.1%gpt-oss-20b
Long context reasoning (AA-LCR)46.7%34.7%GLM 4.5 Air
DTBenchNot measured68.0%Only gpt-oss-20b measured
LMCANot measured14.5%Only gpt-oss-20b measured
LMArena Text13841288GLM 4.5 Air
LMArena Text: instruction following13541236GLM 4.5 Air
LMArena Text: creative writing13431201GLM 4.5 Air
LMArena Text: English13971303GLM 4.5 Air
LMArena Text: non-English13661269GLM 4.5 Air
LMArena Text: Chinese14261315GLM 4.5 Air
LMArena Text: German13771255GLM 4.5 Air
LMArena Text: Japanese13481244GLM 4.5 Air
LMArena Text: Korean13081236GLM 4.5 Air
LMArena Text: French1400Not measuredOnly GLM 4.5 Air measured
LMArena Text: Spanish13851267GLM 4.5 Air
LMArena Text: Russian13731278GLM 4.5 Air
LMArena Text: Polish13681252GLM 4.5 Air
LMArena Text: multi-turn13711268GLM 4.5 Air
LMArena Text: longer queries13661250GLM 4.5 Air
LMArena Text: writing and language13541238GLM 4.5 Air
LMArena Text: entertainment and media13391216GLM 4.5 Air
Neither model has a result on the other 25 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 4.5 Air and gpt-oss-20b
BenchmarkGLM 4.5 Airgpt-oss-20bLeader
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 4.5 Air$0.0008Fits in one request
gpt-oss-20b$0.0001Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

GLM 4.5 Air$0.013Fits in one request
gpt-oss-20b$0.0019Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

GLM 4.5 Air$0.051Exceeds the context window
gpt-oss-20b$0.0075Exceeds the context window

gpt-oss-20b 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 4.5 Air and gpt-oss-20b
SpecificationZ.ai GLM 4.5 AirOpenAI gpt-oss-20b
MakerZ.aiOpenAI
WeightsOpen weightsOpen weights
ReleasedJuly 25, 2025August 5, 2025
Context window131K131K
Input $/Mtok$0.20$0.03
Output $/Mtok$1.10$0.15
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 4.5 Air better than gpt-oss-20b for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GLM 4.5 Air for work measured by LiveCodeBench (Artificial Analysis run) or τ²-Bench Telecom, where it leads.

Which is cheaper, GLM 4.5 Air or gpt-oss-20b?

GLM 4.5 Air costs $0.20 per million input tokens and $1.10 per million output tokens; gpt-oss-20b costs $0.03 and $0.15. Cost per solved task is known for neither of them.

Which has the bigger context window, GLM 4.5 Air or gpt-oss-20b?

Neither: both take 131K tokens.

How many benchmarks is the GLM 4.5 Air vs gpt-oss-20b comparison based on?

41 benchmarks have a result for both models as of October 22, 2026. GLM 4.5 Air's coding index rests on 0 independent benchmarks and gpt-oss-20b's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next