Benchmark suiteUpdated May 27, 2026

GLM 4.6.

A model-level benchmark profile for GLM 4.6, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.

Z.ai lab page

Lab

Z.ai

Open weights

Coverage

67%

6 of 9 tracked signals

Best Arena rank

#54

WebDev Arena

Best suite

#54

Value / 55

Model profile

Benchmark signal map.

This view treats missing values as coverage gaps, then puts every available score, rank, cost, and speed signal into the same visual hierarchy.

Analyst view

GLM 4.6 is strongest on value.

67% coverage

Its best composite result is rank #54 in the value view, with a 55 value index. The strongest raw Arena signal is WebDev Arena at rank #54 with 8,349 public votes.

Best current lane

Value

#54 / 55 value index

Strongest raw signal

Code

#54, 1355 score

Commercial posture

$1.00

1.92s first token / 46 tok/s

Coverage gaps

Vision ArenaSearch ArenaDocument Arena

Profile completeness

6 of 9 signals matched

67%

Arena categories

2/5

Code, Text

Commercial match

Live

GLM-4.6 (Non-reasoning)

SWE-bench

#32

bash-only

Raw identifier

glm-4.6

Open weights

Performance cockpit

Public benchmark scores

Arena rows show score, public rank, confidence interval, vote count, and publish date. Missing rows stay visible as coverage gaps.

Text Arena

Arena category

1,426#72

1422-1430 CI

35,661 votes

May 27, 2026

Arena public leaderboard dataset

WebDev Arena

Arena category

1,355#54

1346-1364 CI

8,349 votes

May 25, 2026

Arena public leaderboard dataset

Vision Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Search Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Document Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

SWE-bench Verified

Software issue resolution

55.4%#32

bash-only

glm-4.6

Dec 1, 2025

SWE-bench Verified

Cost and speed

Commercial profile

Price, latency, and throughput are only shown when a confident commercial source row is matched.

Blended price

$1.00

USD / 1M tokens

Input price

$0.600

USD / 1M input tokens

Output price

$2.20

USD / 1M output tokens

Latency

1.92s

Median time to first token

Output speed

46 tok/s

Median generation speed

Matched source row

GLM-4.6 (Non-reasoning)

Suite position

Composite ranks by benchmark lens.

These views combine available public signals into purpose-specific indexes. A missing card means the model lacks enough source coverage for that lens.

Value

Quality, price, latency, and output speed

#5455

value index

blended / 1M tokens$1.00

time to first token1.92s

output speed46 tok/s

Coding

Code Arena, SWE-bench, and output speed

#5550

coding index

Code Arena rank #541,355