Z.ai: GLM 5.3 Flash

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-conte…

z-ai/glm-5.3-flash-20260826

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.

Specifications & capabilities

Input
text, image, video
Output
text
Context window · tokens
1048576
Published model ID
GLM-5.3-Flash
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput
Description source ↗

Evaluations

61–80 / 90

OpenRouter Benchmarks

86.385%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Phala
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
10
sample size
1895
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
Phala
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:36:30.903Z
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
1895
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.863852179419525
accuracy_std_dev
0.02754414592685712
cost_per_task_usd
0.012207302902374668
output_tokens_per_task
28225.067018469657
latency_seconds_per_task
440.15153984168865
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
24
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

80.282%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Makora
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
10
sample size
1644
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
9
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
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
2026-10-31T08:33:53.031Z
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
1644
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8028182609489051
accuracy_std_dev
0.07654548992882891
cost_per_task_usd
0.019102108272506083
output_tokens_per_task
40420.16605839416
latency_seconds_per_task
309.06923114355226
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-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

78.715%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Sail Research
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
10
sample size
2970
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
15
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
2026-11-06T22:10:48.831Z
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
2970
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7871492666666666
accuracy_std_dev
0.11453375331110427
cost_per_task_usd
0.01689483905723906
output_tokens_per_task
30856.628282828282
latency_seconds_per_task
609.2644754208754
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-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

74.067%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Together
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
10
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
Together
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T12:42:18.186Z
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
0.7406666000000001
accuracy_std_dev
0.018961987708043703
cost_per_task_usd
0.014243233999999999
output_tokens_per_task
4429.298
latency_seconds_per_task
72.756944
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
22
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

73.118%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · DigitalOcean
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
10
sample size
496
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
DigitalOcean
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T12:31:51.998Z
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
496
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7311827782258065
accuracy_std_dev
0.07837008853695393
cost_per_task_usd
0.009883709677419354
output_tokens_per_task
4275.5161290322585
latency_seconds_per_task
170.34814314516132
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
20
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

83.257%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Relace
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
11
sample size
1962
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
Relace
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:26:26.747Z
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
1962
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8325688873598369
accuracy_std_dev
0.019237670701256954
cost_per_task_usd
0.013576182466870541
output_tokens_per_task
39848.997961264016
latency_seconds_per_task
438.29760295616717
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-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

83.135%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Crusoe
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
11
sample size
1684
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
9
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Crusoe
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:55:40.953Z
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
1684
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8313539815914488
accuracy_std_dev
0.013525888763386546
cost_per_task_usd
0.02395000890736342
output_tokens_per_task
47679.917458432305
latency_seconds_per_task
287.5242090261283
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
15
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

82.539%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Modal
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
11
sample size
2140
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
Modal
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:48:01.125Z
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
2140
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.825389385046729
accuracy_std_dev
0.014184335849948446
cost_per_task_usd
0.03383954813084113
output_tokens_per_task
47991.5476635514
latency_seconds_per_task
407.0900654205608
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-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

88.392%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · DeepInfra
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
12
sample size
1298
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
DeepInfra
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:34:49.723Z
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
1298
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8839239383667181
accuracy_std_dev
0.011423232412500406
cost_per_task_usd
0.00878981278890601
output_tokens_per_task
29702.687981510015
latency_seconds_per_task
844.3666594761171
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
71
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

83.307%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Cloudflare
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
12
sample size
1278
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
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Cloudflare
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-03T09:40:53.626Z
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
1278
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8330725023474179
accuracy_std_dev
0.010168177287347969
cost_per_task_usd
0.029710525039123633
output_tokens_per_task
42323.18544600939
latency_seconds_per_task
655.5555469483568
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
18
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

83.185%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · BaseTen
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
12
sample size
2805
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
17
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
BaseTen
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:20:07.217Z
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
2805
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8318478292335116
accuracy_std_dev
0.010811745465322452
cost_per_task_usd
0.020570678431372547
output_tokens_per_task
40944.02673796791
latency_seconds_per_task
255.95605668449198
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
16
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

76%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Novita
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
12
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
Novita
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T12:49:39.925Z
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
0.7599999000000001
accuracy_std_dev
0.030840204640858015
cost_per_task_usd
0.008153706000000002
output_tokens_per_task
4219.412
latency_seconds_per_task
200.97110800000002
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
52
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

85.943%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · DigitalOcean
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
13
sample size
2082
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
DigitalOcean
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:27:46.434Z
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
2082
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.859429902017291
accuracy_std_dev
0.05098775585122179
cost_per_task_usd
0.011825536023054757
output_tokens_per_task
25201.657060518733
latency_seconds_per_task
442.6108179634967
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-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

84.269%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · StreamLake
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
14
sample size
2172
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
StreamLake
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:57:00.536Z
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
2172
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8426947486187845
accuracy_std_dev
0.027181441039645704
cost_per_task_usd
0.01345692311233886
output_tokens_per_task
42267.71869244936
latency_seconds_per_task
682.9847329650091
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
30
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

84.089%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Fireworks
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
14
sample size
3087
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
16
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Fireworks
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:54:15.638Z
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
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
3087
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.840891889212828
accuracy_std_dev
0.01539818649719325
cost_per_task_usd
0.022577127632005183
output_tokens_per_task
38449.29964366699
latency_seconds_per_task
250.1895425979916
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
17
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

82.641%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · CoreWeave
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
15
sample size
1878
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
CoreWeave
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:17:29.105Z
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
1878
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8264111325878595
accuracy_std_dev
0.01425677691801343
cost_per_task_usd
0.02454355484558041
output_tokens_per_task
50263.019169329076
latency_seconds_per_task
264.9671730564431
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
27
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

85.078%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · GMICloud
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
16
sample size
2569
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
13
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
GMICloud
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-10T08:10:11.354Z
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
2569
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8507849505644222
accuracy_std_dev
0.03243006205932389
cost_per_task_usd
0.008747444920202414
output_tokens_per_task
31305.17399766446
latency_seconds_per_task
480.92924172829896
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
26
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

84.067%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · AtlasCloud
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
16
sample size
1386
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
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
AtlasCloud
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:09:30.600Z
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
1386
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8406685714285715
accuracy_std_dev
0.01850043854968342
cost_per_task_usd
0.02123720418470418
output_tokens_per_task
42244.7886002886
latency_seconds_per_task
436.8964862914863
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
30
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

71.394%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · GMICloud
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
16
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
GMICloud
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-10T08:18:49.964Z
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
0.7139393636363637
accuracy_std_dev
0.07661811901688757
cost_per_task_usd
0.010148356363636365
output_tokens_per_task
8765.507272727273
latency_seconds_per_task
242.0070509090909
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-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

OpenRouter Benchmarks

75.503%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · DeepInfra
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
17
sample size
298
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
6
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
DeepInfra
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T12:14:04.084Z
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
298
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7550335167785235
accuracy_std_dev
0.023364430687122125
cost_per_task_usd
0.012232758389261746
output_tokens_per_task
4166.208053691275
latency_seconds_per_task
267.6038926174497
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
63
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-5.3-flash-20260826
source model id
z-ai/glm-5.3-flash-20260826
Original result ↗

Published prices

1–20 / 104

@cf/zai-org/glm-5.3-flash ↗

$0.03

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-5.3-flash ↗

$0.50

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-5.3-flash ↗

$0.03

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

z-ai/glm-5.3-flash ↗

$0.04

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

z-ai/glm-5.3-flash ↗

$0.08

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

z-ai/glm-5.3-flash:batch ↗

$0.01

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
mode
batch

z-ai/glm-5.3-flash:batch ↗

$0.05

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions
mode
batch

z-ai/glm-5.3-flash:batch ↗

$0.18

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions
mode
batch

~z-ai/glm-flash-latest ↗

$0.03

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
alias_target
name
Z.ai: GLM 5.3 Flash
slug
z-ai/glm-5.3-flash
routing_alias
true

~z-ai/glm-flash-latest ↗

$0.04

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions
alias_target
name
Z.ai: GLM 5.3 Flash
slug
z-ai/glm-5.3-flash
routing_alias
true

~z-ai/glm-flash-latest ↗

$0.08

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions
alias_target
name
Z.ai: GLM 5.3 Flash
slug
z-ai/glm-5.3-flash
routing_alias
true

zai-org/GLM-5.3-Flash ↗

$0.03

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-5.3-Flash ↗

$0.15

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

zai-org/GLM-5.3-Flash ↗

$0.50

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

zai/glm-5.3-flash ↗

$0.03

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
baseten | zai/glm-5.3-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.3-flash ↗

$0.03

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-5.3-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.3-flash ↗

$0.15

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
baseten | zai/glm-5.3-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.3-flash ↗

$0.15

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
input_tokens_per_million
Currency
USD
Billing conditions
region
scope
zone
geo_region
us
endpoint
baseten | zai/glm-5.3-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.3-flash ↗

$0.50

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
baseten | zai/glm-5.3-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-5.3-flash ↗

$0.50

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
output_tokens_per_million
Currency
USD
Billing conditions
region
scope
zone
geo_region
us
endpoint
baseten | zai/glm-5.3-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–7 / 7

zai-org/GLM-5.3-Flash ↗

source model id
azure-huggingface/zai-org--glm-5.3-flash@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
MIT
context length
524288
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities

    zai-org/GLM-5.3-Flash ↗

    source model id
    azure-huggingface/zai-org--glm-5.3-flash@2
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    license
    MIT
    context length
    524288
    architecture
    input_modalities
    • text
    • image
    output_modalities
    • text
    capabilities

      glm-5.3-flash ↗

      source model id
      @cf/zai-org/glm-5.3-flash
      hosting
      cloudflare-hosted
      platforms
      • Cloudflare Workers AI
      context length
      1048576
      architecture
      input_modalities
      • text
      • image
      output_modalities
      • text
      capabilities
      • toolCalling

      GLM-5.3-Flash ↗

      source model id
      publishers/zai-org/models/glm-5-3@glm-5.3-flash
      hosting
      vertex-self-deployed
      platforms
      • Google Cloud Vertex AI
      architecture
      input_modalities
      • text
      output_modalities
      • text
      capabilities

        glm-5-3-flash ↗

        source model id
        z-ai/glm-5-3-flash
        hosting
        nvidia-catalog
        platforms
        • NVIDIA Build / NIM
        context length
        1048576
        architecture
        input_modalities
        • text
        • image
        output_modalities
        • text
        capabilities
        • toolCalling
        • structuredOutputs
        • reasoning

        GLM 5.3 Flash ↗

        source model id
        zai/glm-5.3-flash
        hosting
        vercel-gateway
        platforms
        • Vercel AI Gateway
        context length
        1000000
        max output tokens
        131000
        architecture
        input_modalities
        • text
        • image
        • video
        output_modalities
        • text
        capabilities
        • promptCaching
        • reasoning
        • structuredOutputs
        • toolCalling
        • videoInput
        • visionInput
        regions
        • us

        GLM-5.3-Flash ↗

        source model id
        zai-org/GLM-5.3-Flash
        hosting
        siliconflow-hosted
        platforms
        • SiliconFlow
        max output tokens
        262144
        architecture
        input_modalities
        • text
        • image
        output_modalities
        • text
        capabilities
        • promptCaching
        • reasoning
        • structuredOutputs
        • toolCalling

        Source specification observations

        1–13 / 13

        azureFoundry ↗

        field
        context_length
        value
        524288
        normalized value
        524288
        scope
        source-model
        source id
        azureFoundry
        confidence
        1

        azureFoundry ↗

        field
        context_length
        value
        524288
        normalized value
        524288
        scope
        source-model
        source id
        azureFoundry
        confidence
        1

        nvidiaNim ↗

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

        openRouter ↗

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

        openRouter ↗

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

        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
        131072
        normalized value
        131072
        scope
        source-model
        source id
        openRouter
        confidence
        1

        openRouter ↗

        field
        max_output_tokens
        value
        131072
        normalized value
        131072
        scope
        source-model
        source id
        openRouter
        confidence
        1

        openRouter ↗

        field
        max_output_tokens
        value
        131072
        normalized value
        131072
        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
        131000
        normalized value
        131000
        scope
        source-model
        source id
        vercelAIGatewayCatalog
        confidence
        1

        Original sources

        1–20 / 29

        SiliconFlow · Model page ↗

        z.ai · Model reference ↗

        Hugging Face · Model repository ↗

        Cloudflare AI · Model page ↗

        Google Cloud · Model page ↗

        Microsoft Foundry · Model page ↗

        Microsoft Foundry · Model page ↗

        NVIDIA · Model page ↗

        OpenRouter · Model page ↗

        OpenRouter · Model page ↗

        SiliconFlow · Playground ↗

        Vercel AI Gateway · Model page ↗

        Microsoft Foundry · Model documentation ↗

        NVIDIA · Documentation ↗

        SiliconFlow · API documentation ↗

        arXiv · Paper · 2602.15763 ↗

        GitHub · Source snapshot ↗

        Cloudflare AI · Catalog ↗

        Epoch AI · Catalog ↗

        Google Cloud · Catalog ↗

        Source links

        1–13 / 13

        Hugging Face model card

        1–1 / 1

        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