Z.ai: GLM 5.2

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineerin…

z-ai/glm-5.2-20260616

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation.

Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.

Specifications & capabilities

Input
text
Output
text
Context window · tokens
1048576
Published model ID
GLM-5.2
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling
Description source ↗

Evaluations

1–20 / 69

OpenRouter Benchmarks

76.933%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Morph
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
1
sample size
500
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
10
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Morph
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T19:58:49.610Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
500
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7693333
accuracy_std_dev
0.039350196385914006
cost_per_task_usd
0.087123052
output_tokens_per_task
16723.342
latency_seconds_per_task
282.737078
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
9
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

83.291%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Friendli
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
2
sample size
2341
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
12
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Friendli
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T16:06:46.433Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
2341
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8329060884237507
accuracy_std_dev
0.015886988525511157
cost_per_task_usd
0.2567825809483127
output_tokens_per_task
58144.50192225545
latency_seconds_per_task
427.38535027765914
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
7
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

85.523%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Ambient
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
3
sample size
1545
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
8
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Ambient
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T16:11:17.543Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1545
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8552316718446601
accuracy_std_dev
0.0035618211195257714
cost_per_task_usd
0.0868813637540453
output_tokens_per_task
43299.1715210356
latency_seconds_per_task
692.6407055016181
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
4
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

83.9%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Mistral
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
3
sample size
7324
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
37
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Mistral
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-11T03:18:20.413Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
7324
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8389995344074279
accuracy_std_dev
0.011455015921374732
cost_per_task_usd
0.26465632960131075
output_tokens_per_task
57439.03536318951
latency_seconds_per_task
285.33527007099946
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
5
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

76%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Makora
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
3
sample size
100
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Makora
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-08-26T00:00:05.638Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
100
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.76
accuracy_std_dev
0.0066669999999999785
cost_per_task_usd
0.07038507
output_tokens_per_task
10045.27
latency_seconds_per_task
256.30249
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
11
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

69.429%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Ambient
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
3
sample size
350
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
7
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Ambient
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T20:09:59.492Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
350
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.6942857142857143
accuracy_std_dev
0.025305290602753317
cost_per_task_usd
0.049070077142857146
output_tokens_per_task
8147.505714285714
latency_seconds_per_task
249.23163428571428
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
4
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

86.295%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Inceptron
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
4
sample size
1936
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
10
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Inceptron
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T16:16:35.161Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1936
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8629476002066115
accuracy_std_dev
0.031092890107547094
cost_per_task_usd
0.13384704958677685
output_tokens_per_task
43979.465392561986
latency_seconds_per_task
479.3464189049587
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
6
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

69%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Mistral
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
4
sample size
1700
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
34
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Mistral
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-11T03:23:11.016Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1700
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.6899999117647057
accuracy_std_dev
0.026333763959163144
cost_per_task_usd
0.10328957000000001
output_tokens_per_task
9525.96294117647
latency_seconds_per_task
78.25903647058824
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
5
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

89.31%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · DigitalOcean
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
5
sample size
2376
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
12
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
DigitalOcean
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T16:16:10.979Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
2376
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8930975833333333
accuracy_std_dev
0.02298558731559965
cost_per_task_usd
0.08767985311447812
output_tokens_per_task
39812.03493265993
latency_seconds_per_task
506.727319023569
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
23
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

87.721%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Reka
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
5
sample size
623
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
4
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Reka
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-09-30T11:37:23.219Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
623
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8772070529695024
accuracy_std_dev
0.03893659390197737
cost_per_task_usd
0.09425666452648475
output_tokens_per_task
23922.329052969504
latency_seconds_per_task
461.3752568218299
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
13
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

83.471%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Z.AI
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
5
sample size
2178
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
11
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Z.AI
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T16:18:48.433Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
2178
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8347106363636364
accuracy_std_dev
0.07009507473200917
cost_per_task_usd
0.21278814876033061
output_tokens_per_task
48358.50367309458
latency_seconds_per_task
570.2942180899907
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
8
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

69.455%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Friendli
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
5
sample size
550
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
11
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Friendli
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T19:47:27.755Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
550
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.6945454545454546
accuracy_std_dev
0.05278641023693957
cost_per_task_usd
0.11215429818181818
output_tokens_per_task
9316.025454545455
latency_seconds_per_task
85.0663509090909
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
7
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

89.67%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Wafer
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
6
sample size
3911
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
20
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Wafer
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T16:18:08.626Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
3911
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8967014333929941
accuracy_std_dev
0.03454965314283198
cost_per_task_usd
0.37683498056762965
output_tokens_per_task
57557.85144464331
latency_seconds_per_task
497.5562656609563
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
13
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

88.021%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Venice
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
6
sample size
2176
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
11
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Venice
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T16:32:36.327Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
2176
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8802082288602942
accuracy_std_dev
0.029715678021281344
cost_per_task_usd
0.17839703079044117
output_tokens_per_task
40400.66819852941
latency_seconds_per_task
356.4215234375
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
39
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

69.576%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Inceptron
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
6
sample size
550
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
11
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Inceptron
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T19:41:05.183Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
550
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.6957576363636363
accuracy_std_dev
0.027600759894916997
cost_per_task_usd
0.07744747818181819
output_tokens_per_task
9554.076363636364
latency_seconds_per_task
159.60520727272728
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
6
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

85.396%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Decart
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
7
sample size
2699
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
14
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Decart
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-24T16:29:51.093Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
2699
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8539581570952205
accuracy_std_dev
0.020366121093319547
cost_per_task_usd
0.22091287662097076
output_tokens_per_task
44279.295294553536
latency_seconds_per_task
240.85518228973692
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
9
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

74%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Sail Research
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
7
sample size
100
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Sail Research
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-08-29T08:25:32.049Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
100
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.74
accuracy_std_dev
0.020000000000000018
cost_per_task_usd
0.049803139999999996
output_tokens_per_task
8150.99
latency_seconds_per_task
363.44884
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
11
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

70%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Z.AI
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
7
sample size
500
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
10
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Z.AI
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T19:55:04.254Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
500
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7000001
accuracy_std_dev
0.02170498150863068
cost_per_task_usd
0.124576664
output_tokens_per_task
11905.278
latency_seconds_per_task
163.36862
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
8
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

85.614%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Baidu
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
8
sample size
4356
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
22
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Baidu
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-10T19:22:00.700Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
4356
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8561370454545454
accuracy_std_dev
0.0107404034056508
cost_per_task_usd
0.15750592470156105
output_tokens_per_task
45571.12006427915
latency_seconds_per_task
443.79432438016534
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
12
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

OpenRouter Benchmarks

84.848%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Sail Research
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
8
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Sail Research
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-08-29T11:19:17.684Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8484845
accuracy_std_dev
0.005050500000000013
cost_per_task_usd
0.09501090909090909
output_tokens_per_task
30402.136363636364
latency_seconds_per_task
411.875595959596
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
11
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.2-20260616
source model id
z-ai/glm-5.2-20260616
Original result ↗

Published prices

1–20 / 74

@cf/zai-org/glm-5.2 ↗

$0.26

Inference provider
cloudflareWorkersAI
Platform
Cloudflare Workers AI
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
per M cached input tokens

@cf/zai-org/glm-5.2 ↗

$4.40

Inference provider
cloudflareWorkersAI
Platform
Cloudflare Workers AI
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
per M output tokens

z-ai/glm-5.2 ↗

$0.01

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

z-ai/glm-5.2 ↗

$0.01

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

z-ai/glm-5.2 ↗

$6.80

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

zai-org/GLM-5.2 ↗

$0.26

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
Billing label
Cached input tokens (per 1M)

zai-org/GLM-5.2 ↗

$1.30

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
Input tokens (per 1M)

zai-org/GLM-5.2 ↗

$4.09

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
Output tokens (per 1M)

zai/glm-5.2 ↗

$0.28

Inference provider
vercelAIGatewayCatalog
Platform
alibaba
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
alibaba | zai/glm-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.2 ↗

$1.40

Inference provider
vercelAIGatewayCatalog
Platform
alibaba
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
alibaba | zai/glm-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.2 ↗

$4.40

Inference provider
vercelAIGatewayCatalog
Platform
alibaba
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
alibaba | zai/glm-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.2 ↗

$0.14

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
baseten | zai/glm-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.2 ↗

$0.14

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
region
scope
zone
geo_region
us
endpoint
baseten | zai/glm-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.2 ↗

$1.40

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
baseten | zai/glm-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.2 ↗

$1.40

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
input_tokens_per_million
Currency
USD
Billing conditions
region
scope
zone
geo_region
us
endpoint
baseten | zai/glm-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.2 ↗

$4.40

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
baseten | zai/glm-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.2 ↗

$4.40

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
output_tokens_per_million
Currency
USD
Billing conditions
region
scope
zone
geo_region
us
endpoint
baseten | zai/glm-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.2 ↗

$0.11

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | zai/glm-5.2
model_type
language
quantization
fp4
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.2 ↗

$0.56

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | zai/glm-5.2
model_type
language
quantization
fp4
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.2 ↗

$1.80

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | zai/glm-5.2
model_type
language
quantization
fp4
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–5 / 5

glm-5.2 ↗

source model id
@cf/zai-org/glm-5.2
hosting
cloudflare-hosted
platforms
  • Cloudflare Workers AI
context length
262144
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • toolCalling

GLM-5.2 ↗

source model id
glm-5.2
hosting
supernova-hosted
platforms
  • Supernova Labs
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • reasoning
  • promptCaching

GLM 5.2 ↗

source model id
publishers/zai-org/models/glm-5.2-maas@001
hosting
vertex-managed
platforms
  • Google Cloud Vertex AI
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling

GLM 5.2 ↗

source model id
zai/glm-5.2
hosting
vercel-gateway
platforms
  • Vercel AI Gateway
context length
1000000
max output tokens
128000
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • promptCaching
  • reasoning
  • structuredOutputs
  • toolCalling
regions
  • us

GLM-5.2 ↗

source model id
zai-org/GLM-5.2
hosting
siliconflow-hosted
platforms
  • SiliconFlow
max output tokens
262144
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • promptCaching
  • reasoning
  • toolCalling

Source specification observations

1–6 / 6

openRouter ↗

field
context_length
value
1048576
normalized value
1048576
scope
source-model
source id
openRouter
confidence
1

siliconFlow ↗

field
context_length
value
1049K
scope
source-model
source id
siliconFlow
confidence
1

vercelAIGatewayCatalog ↗

field
context_length
value
1000000
normalized value
1000000
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

openRouter ↗

field
max_output_tokens
value
943718
normalized value
943718
scope
source-model
source id
openRouter
confidence
1

siliconFlow ↗

field
max_output_tokens
value
262K
scope
source-model
source id
siliconFlow
confidence
1

vercelAIGatewayCatalog ↗

field
max_output_tokens
value
128000
normalized value
128000
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

Original sources

21–22 / 22

Supernova · Catalog ↗

Vercel AI Gateway · Catalog ↗

Source links

1–12 / 12

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace