Enter opens the highlighted result. Esc closes.

GLM 5 vs gpt-oss-20b

GLM 5 leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 27.9 to 10.0, and gpt-oss-20b costs 21.3x less per output token ($0.15 vs $3.20 per million). Updated October 21, 2026; 52 benchmarks have a result for both.

Replace GLM 5 Replace gpt-oss-20b
GLM 5Z.ai
Coding
41.7
Overall
54.3
Output $/M
$3.20
52
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
0
vs boards won of 52 shared

GLM 5 or gpt-oss-20b: which to pick

Only GLM 5 has a coding score, 41.7 on the Vibe Coding Index; gpt-oss-20b has none, so the two cannot be ranked on coding.

Pick gpt-oss-20b for output tokens 21.3x cheaper ($0.15 vs $3.20 per million).

Model AGLM 5Z.ai41.7/1003 independent benchmarks$0.63 per solved taskModel Bgpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
52
GLM 5 only
24
gpt-oss-20b only
10
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 5 41.7 from 3 benchmarks, gpt-oss-20b not benchmarked.
Widest category
Web design, 43.1 points apart on average over 2 shared benchmarks.
Widest single gap
Design Arena: websites: GLM 5 1247 against gpt-oss-20b 852, 49.4 points apart on a 0 to 100 scale.
Output price
GLM 5 $3.20 against gpt-oss-20b $0.15 per million output tokens, 21.3x apart.
Context window
GLM 5 takes 205K tokens, gpt-oss-20b 131K.

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 5Barsgpt-oss-20bTies
Coding70
Intelligence20
Agentic work10
Reasoning80
Math40
Knowledge100
Web design20
General180
All shared boards520
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
Coding benchmarks for GLM 5 and gpt-oss-20b
BenchmarkGLM 5gpt-oss-20bLeader
SWE-bench Verified72.8%Not measuredOnly GLM 5 measured
SWE-bench Multilingual69.7%Not measuredOnly GLM 5 measured
LMArena WebDev1435Not measuredOnly GLM 5 measured
LiveCodeBench (Vals AI)81.9%80.4%GLM 5
SWE-bench Verified (Vals AI)71.4%Not measuredOnly GLM 5 measured
Vibe Code Bench (Vals AI)23.4%Not measuredOnly GLM 5 measured
LiveCodeBench (Artificial Analysis run)Not measured77.7%Only gpt-oss-20b measured
SciCodeNot measured38.9%Only gpt-oss-20b measured
Terminal-Bench Hard (Artificial Analysis run)43.2%10.6%GLM 5
Terminal-Bench52.4%3.4%GLM 5
WeirdML48.2%40.9%GLM 5
ALE-Bench765.6566.0GLM 5
LMArena Text: coding14611307GLM 5
LMArena Text: software and IT14601311GLM 5
LMArena WebDev: React1424Not measuredOnly GLM 5 measured
LMArena WebDev: HTML1450Not measuredOnly GLM 5 measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GLM 5 and gpt-oss-20b
BenchmarkGLM 5gpt-oss-20bLeader
AA Intelligence Index27.910.0GLM 5
Epoch Capabilities Index145.8137.7GLM 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GLM 5 and gpt-oss-20b
BenchmarkGLM 5gpt-oss-20bLeader
Design Arena: agents building full-stack apps1123Not measuredOnly GLM 5 measured
Design Arena: agents building mobile apps1136Not measuredOnly GLM 5 measured
Design Arena: agents building Android apps1146Not measuredOnly GLM 5 measured
Design Arena: agents building Godot games1144Not measuredOnly GLM 5 measured
Design Arena: HTML slides1148Not measuredOnly GLM 5 measured
τ²-Bench Telecom98.2%60.2%GLM 5
Vending-Bench 2$4,432Not measuredOnly GLM 5 measured
BrowseComp-PlusNot measured50.6%Only gpt-oss-20b measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index80
Reasoning benchmarks for GLM 5 and gpt-oss-20b
BenchmarkGLM 5gpt-oss-20bLeader
GPQA Diamond83.3%68.9%GLM 5
GPQA Diamond (Artificial Analysis run)82.0%68.8%GLM 5
Humanity's Last Exam (Artificial Analysis run)29.3%11.0%GLM 5
GPQA Diamond (Epoch AI run)87.8%60.8%GLM 5
ARC-AGI44.7%Not measuredOnly GLM 5 measured
ARC-AGI-24.9%Not measuredOnly GLM 5 measured
SimpleBench53.2%Not measuredOnly GLM 5 measured
LMArena Text: hard prompts14521274GLM 5
LMArena Text: expert14541258GLM 5
LMArena Text: hard prompts in English14601292GLM 5
Kagi LLM Benchmark75.0%53.2%GLM 5
Neither model has a result on the other 11 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for GLM 5 and gpt-oss-20b
BenchmarkGLM 5gpt-oss-20bLeader
AIME91.7%86.0%GLM 5
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 IndexNot measured89.3Only gpt-oss-20b measured
AIME 2025 (Artificial Analysis run)Not measured89.3%Only gpt-oss-20b measured
OTIS Mock AIME80.0%65.3%GLM 5
LMArena Text: math14401317GLM 5
LMArena Text: mathematical work14511305GLM 5
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100
Knowledge benchmarks for GLM 5 and gpt-oss-20b
BenchmarkGLM 5gpt-oss-20bLeader
MMLU Pro86.0%71.6%GLM 5
LegalBench (Vals AI)84.1%70.8%GLM 5
CaseLaw (Vals AI)52.5%43.8%GLM 5
CorpFin (Vals AI)62.9%53.1%GLM 5
TaxEval (Vals AI)70.0%63.7%GLM 5
MedQA (Vals AI)94.3%82.9%GLM 5
MMLU Pro (Artificial Analysis run)Not measured74.8%Only gpt-oss-20b measured
LMArena Text: science14601296GLM 5
LMArena Text: medicine and healthcare14551310GLM 5
LMArena Text: legal and government14531280GLM 5
LMArena Text: business and finance14301284GLM 5
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 5 and gpt-oss-20b
BenchmarkGLM 5gpt-oss-20bLeader
Design Arena: websites1247852GLM 5
Design Arena: UI components1230Not measuredOnly GLM 5 measured
Design Arena: game dev1234Not measuredOnly GLM 5 measured
Design Arena: data viz1228933GLM 5
Design Arena: 3D1229Not measuredOnly GLM 5 measured
Design Arena: all code categories1246Not measuredOnly GLM 5 measured
Design Arena: SVG1168Not measuredOnly GLM 5 measured
Design Arena: ASCII art1147Not measuredOnly GLM 5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index180
General benchmarks for GLM 5 and gpt-oss-20b
BenchmarkGLM 5gpt-oss-20bLeader
IFBench72.3%65.1%GLM 5
Long context reasoning (AA-LCR)75.7%34.7%GLM 5
DTBenchNot measured68.0%Only gpt-oss-20b measured
LMCANot measured14.5%Only gpt-oss-20b measured
CL-bench18.7%Not measuredOnly GLM 5 measured
LMArena Text14461288GLM 5
LMArena Text: instruction following14281236GLM 5
LMArena Text: creative writing14381201GLM 5
LMArena Text: English14581303GLM 5
LMArena Text: non-English14301269GLM 5
LMArena Text: Chinese15111315GLM 5
LMArena Text: German14471255GLM 5
LMArena Text: Japanese14161244GLM 5
LMArena Text: Korean14231236GLM 5
LMArena Text: French1456Not measuredOnly GLM 5 measured
LMArena Text: Spanish14541267GLM 5
LMArena Text: Russian14361278GLM 5
LMArena Text: Polish14341252GLM 5
LMArena Text: multi-turn14561268GLM 5
LMArena Text: longer queries14461250GLM 5
LMArena Text: writing and language14371238GLM 5
LMArena Text: entertainment and media14261216GLM 5
Neither model has a result on the other 24 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 5 and gpt-oss-20b
BenchmarkGLM 5gpt-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 5$0.0026Fits in one request
gpt-oss-20b$0.0001Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

GLM 5$0.060Fits in one request
gpt-oss-20b$0.0019Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

GLM 5$0.232Exceeds 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 5 and gpt-oss-20b
SpecificationZ.ai GLM 5OpenAI gpt-oss-20b
MakerZ.aiOpenAI
WeightsOpen weightsOpen weights
ReleasedFebruary 11, 2026August 5, 2025
Context window205K131K
Input $/Mtok$1.00$0.03
Output $/Mtok$3.20$0.15
Coding index41.7Not benchmarked
Independent measurements behind it30
Cost per solved task$0.63Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 5 better than gpt-oss-20b for coding?

Only GLM 5 has a coding score, 41.7 on the Vibe Coding Index; gpt-oss-20b has none, so the two cannot be ranked on coding. Pick gpt-oss-20b for output tokens 21.3x cheaper ($0.15 vs $3.20 per million).

Which is cheaper, GLM 5 or gpt-oss-20b?

GLM 5 costs $1.00 per million input tokens and $3.20 per million output tokens; gpt-oss-20b costs $0.03 and $0.15. Cost per solved task is known for GLM 5 only.

Which has the bigger context window, GLM 5 or gpt-oss-20b?

GLM 5, with 205K tokens against 131K.

How many benchmarks is the GLM 5 vs gpt-oss-20b comparison based on?

52 benchmarks have a result for both models as of October 21, 2026. GLM 5's coding index rests on 3 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