Enter opens the highlighted result. Esc closes.

GLM 4.6V vs Step 3.5 Flash

Updated October 21, 2026. 27 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GLM 4.6V Replace Step 3.5 Flash
GLM 4.6VZ.ai
Coding
No data
Overall
11.2
Output $/M
$0.90
0
Step 3.5 FlashStepFun
Coding
No data
Overall
17.0
Output $/M
$0.30
27
vs boards won of 27 shared

Decision reading

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

GLM 4.6V has the edge where what matters is Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.

Model AGLM 4.6VZ.aiNot benchmarkedNo coding benchmarkNo cost per solved taskModel BStep 3.5 FlashStepFunNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
27
GLM 4.6V only
11
Step 3.5 Flash only
8
Like-for-like categories
6 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 4.6V not benchmarked, Step 3.5 Flash not benchmarked.
Widest category
Agentic work, 62.9 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: GLM 4.6V 31.6% against Step 3.5 Flash 94.4%, 62.9 points apart on a 0 to 100 scale.
Output price
GLM 4.6V $0.90 against Step 3.5 Flash $0.30 per million output tokens, 3.0x apart.
Context window
GLM 4.6V takes 131K tokens, Step 3.5 Flash 262K.

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 4.6VBarsStep 3.5 FlashTies
Coding03
Intelligence01
Agentic work01
Reasoning05
Knowledge04
General013
All shared boards027
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for GLM 4.6V and Step 3.5 Flash
BenchmarkGLM 4.6VStep 3.5 FlashLeader
LiveCodeBench (Artificial Analysis run)41.1%Not measuredOnly GLM 4.6V measured
Terminal-Bench Hard (Artificial Analysis run)14.4%32.6%Step 3.5 Flash
LMArena Text: coding13891436Step 3.5 Flash
LMArena Text: software and IT13911434Step 3.5 Flash
Neither model has a result on the other 34 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GLM 4.6V and Step 3.5 Flash
BenchmarkGLM 4.6VStep 3.5 FlashLeader
AA Intelligence Index11.217.0Step 3.5 Flash
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GLM 4.6V and Step 3.5 Flash
BenchmarkGLM 4.6VStep 3.5 FlashLeader
τ²-Bench Telecom31.6%94.4%Step 3.5 Flash
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for GLM 4.6V and Step 3.5 Flash
BenchmarkGLM 4.6VStep 3.5 FlashLeader
GPQA Diamond (Artificial Analysis run)71.9%83.1%Step 3.5 Flash
Humanity's Last Exam (Artificial Analysis run)9.6%24.5%Step 3.5 Flash
LMArena Text: hard prompts13671411Step 3.5 Flash
LMArena Text: expert13711421Step 3.5 Flash
LMArena Text: hard prompts in English13911421Step 3.5 Flash
LMArena Vision: diagrams1182Not measuredOnly GLM 4.6V measured
LMArena Vision: homework1155Not measuredOnly GLM 4.6V measured
Neither model has a result on the other 14 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Math benchmarks for GLM 4.6V and Step 3.5 Flash
BenchmarkGLM 4.6VStep 3.5 FlashLeader
AA Math Index85.3Not measuredOnly GLM 4.6V measured
AIME 2025 (Artificial Analysis run)85.3%Not measuredOnly GLM 4.6V measured
LMArena Text: mathNot measured1408Only Step 3.5 Flash measured
LMArena Text: mathematical workNot measured1421Only Step 3.5 Flash measured
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for GLM 4.6V and Step 3.5 Flash
BenchmarkGLM 4.6VStep 3.5 FlashLeader
MMLU Pro (Artificial Analysis run)79.9%Not measuredOnly GLM 4.6V measured
LMArena Text: science13891415Step 3.5 Flash
LMArena Text: medicine and healthcare13891408Step 3.5 Flash
LMArena Text: legal and government13931408Step 3.5 Flash
LMArena Text: business and finance13591394Step 3.5 Flash
Neither model has a result on the other 12 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for GLM 4.6V and Step 3.5 Flash
BenchmarkGLM 4.6VStep 3.5 FlashLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index013
General benchmarks for GLM 4.6V and Step 3.5 Flash
BenchmarkGLM 4.6VStep 3.5 FlashLeader
IFBench30.1%66.5%Step 3.5 Flash
Long context reasoning (AA-LCR)48.7%63.0%Step 3.5 Flash
LMArena Text13761403Step 3.5 Flash
LMArena Text: instruction following13501385Step 3.5 Flash
LMArena Text: creative writing13471357Step 3.5 Flash
LMArena Vision1164Not measuredOnly GLM 4.6V measured
LMArena Text: English13951417Step 3.5 Flash
LMArena Text: non-English13581385Step 3.5 Flash
LMArena Text: Chinese14251446Step 3.5 Flash
LMArena Text: GermanNot measured1405Only Step 3.5 Flash measured
LMArena Text: JapaneseNot measured1353Only Step 3.5 Flash measured
LMArena Text: KoreanNot measured1351Only Step 3.5 Flash measured
LMArena Text: FrenchNot measured1421Only Step 3.5 Flash measured
LMArena Text: SpanishNot measured1419Only Step 3.5 Flash measured
LMArena Text: Russian13391385Step 3.5 Flash
LMArena Text: PolishNot measured1389Only Step 3.5 Flash measured
LMArena Text: multi-turn13591404Step 3.5 Flash
LMArena Text: longer queries13571402Step 3.5 Flash
LMArena Text: writing and language13471372Step 3.5 Flash
LMArena Text: entertainment and media13431360Step 3.5 Flash
LMArena Vision: English1179Not measuredOnly GLM 4.6V measured
LMArena Vision: Chinese1217Not measuredOnly GLM 4.6V measured
LMArena Vision: reading text1171Not measuredOnly GLM 4.6V measured
LMArena Vision: creative writing1113Not measuredOnly GLM 4.6V 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 4.6V and Step 3.5 Flash
BenchmarkGLM 4.6VStep 3.5 FlashLeader
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 4.6V$0.0008Fits in one request
Step 3.5 Flash$0.0003Fits in one request

Step 3.5 Flash costs less

Repository review

50K input + 3K output tokens

GLM 4.6V$0.018Fits in one request
Step 3.5 Flash$0.0059Fits in one request

Step 3.5 Flash costs less

Agent loop

200K input + 10K output tokens

GLM 4.6V$0.069Exceeds the context window
Step 3.5 Flash$0.023Fits in one request

Step 3.5 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 4.6V and Step 3.5 Flash
SpecificationZ.ai GLM 4.6VStepFun Step 3.5 Flash
MakerZ.aiStepFun
WeightsOpen weightsOpen weights
ReleasedDecember 8, 2025January 29, 2026
Context window131K262K
Input $/Mtok$0.30$0.10
Output $/Mtok$0.90$0.30
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 4.6V better than Step 3.5 Flash for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. GLM 4.6V has the edge where what matters is Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.

Which is cheaper, GLM 4.6V or Step 3.5 Flash?

GLM 4.6V costs $0.30 per million input tokens and $0.90 per million output tokens; Step 3.5 Flash costs $0.10 and $0.30. Cost per solved task is known for neither of them.

Which has the bigger context window, GLM 4.6V or Step 3.5 Flash?

Step 3.5 Flash, with 262K tokens against 131K.

How many benchmarks is the GLM 4.6V vs Step 3.5 Flash comparison based on?

27 benchmarks have a result for both models as of October 21, 2026. GLM 4.6V's coding index rests on 0 independent benchmarks and Step 3.5 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next