Z.ai: GLM 4.6

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex…

z-ai/glm-4.6

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...

Specifications & capabilities

Input
text
Output
text
Context window · tokens
204800
Published model ID
GLM-4.6
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Evaluations

21–30 / 30

OpenRouter Benchmarks

69.524%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Venice
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
31
sample size
1365
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
Venice
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T16:23:19.099Z
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
1365
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.6952379824175824
accuracy_std_dev
0.04288600202768226
cost_per_task_usd
0.031070087912087915
output_tokens_per_task
18572.407326007327
latency_seconds_per_task
755.5303274725275
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-4.6
source model id
z-ai/glm-4.6
Original result ↗

BFCL

84.96%

source id
bfcl
leaderboard name
BFCL Irrelevance Detection
dimension
toolUse
metric
Irrelevance detection
rank
33
Original result ↗

OpenRouter Benchmarks

78.242%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · DeepInfra
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
33
sample size
1090
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
2026-10-31T16:04:29.123Z
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
1090
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7824160174311926
accuracy_std_dev
0.017840425618521553
cost_per_task_usd
0.04672766880733945
output_tokens_per_task
23260.208256880735
latency_seconds_per_task
971.0107899082568
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-4.6
source model id
z-ai/glm-4.6
Original result ↗

OpenRouter Benchmarks

69.263%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · DeepInfra
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
39
sample size
199
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
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
2026-10-31T21:01:44.534Z
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
199
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.6926297185929648
accuracy_std_dev
0.014566408256670558
cost_per_task_usd
0.04924894974874372
output_tokens_per_task
8270.989949748744
latency_seconds_per_task
416.469095477387
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-4.6
source model id
z-ai/glm-4.6
Original result ↗

OpenRouter Benchmarks

71.905%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · auto-routing
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
61
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
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T20:46:45.843Z
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
0.7190477142857142
accuracy_std_dev
0.014443512619010297
cost_per_task_usd
0.052984574285714285
output_tokens_per_task
9361.582857142857
latency_seconds_per_task
384.2272342857143
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
128
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-4.6
source model id
z-ai/glm-4.6
Original result ↗

BFCL

75%

source id
bfcl
leaderboard name
BFCL Relevance Detection
dimension
toolUse
metric
Relevance detection
rank
66
Original result ↗

OpenRouter Benchmarks

77.056%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · auto-routing
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
89
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
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T16:08:31.065Z
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
0.7705627142857142
accuracy_std_dev
0.03293717088949932
cost_per_task_usd
0.06274982683982684
output_tokens_per_task
30923.48124098124
latency_seconds_per_task
1017.904803030303
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
132
benchmark_evaluation
true
openrouter_permaslug
z-ai/glm-4.6
source model id
z-ai/glm-4.6
Original result ↗

SWE-bench

55.4%

source id
sweBench
leaderboard name
SWE-bench Verified
dimension
coding
metric
Resolved tasks
rank
92
sample size
500
evaluated at
2025-12-01T00:00:00.000Z
Original result ↗

Published prices

1–17 / 17

zai-org/GLM-4.6 ↗

$0.50

Inference provider
deepInfra
Platform
DeepInfra
Unit
input_tokens_per_million
Currency
USD
Billing conditions

zai-org/GLM-4.6 ↗

$2.00

Inference provider
deepInfra
Platform
DeepInfra
Unit
output_tokens_per_million
Currency
USD
Billing conditions

z-ai/glm-4.6 ↗

$0.10

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

z-ai/glm-4.6 ↗

$0.50

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

z-ai/glm-4.6 ↗

$2.00

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

zai/glm-4.6 ↗

$0.10

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | zai/glm-4.6
model_type
language
quantization
fp4
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

zai/glm-4.6 ↗

$0.50

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | zai/glm-4.6
model_type
language
quantization
fp4
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-4.6 ↗

$2.00

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | zai/glm-4.6
model_type
language
quantization
fp4
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-4.6 ↗

$0.11

Inference provider
vercelAIGatewayCatalog
Platform
novita
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
novita | zai/glm-4.6
model_type
language
quantization
bf16
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

zai/glm-4.6 ↗

$0.55

Inference provider
vercelAIGatewayCatalog
Platform
novita
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
novita | zai/glm-4.6
model_type
language
quantization
bf16
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-4.6 ↗

$2.20

Inference provider
vercelAIGatewayCatalog
Platform
novita
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
novita | zai/glm-4.6
model_type
language
quantization
bf16
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-4.6 ↗

$0.11

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
varies_by_provider
true
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

zai/glm-4.6 ↗

$0.60

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
input_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
varies_by_provider
true
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-4.6 ↗

$2.20

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
varies_by_provider
true
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-4.6 ↗

$0.11

Inference provider
vercelAIGatewayCatalog
Platform
zai
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
zai | zai/glm-4.6
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

zai/glm-4.6 ↗

$0.60

Inference provider
vercelAIGatewayCatalog
Platform
zai
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
zai | zai/glm-4.6
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

zai/glm-4.6 ↗

$2.20

Inference provider
vercelAIGatewayCatalog
Platform
zai
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
zai | zai/glm-4.6
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–6 / 6

zai-org/GLM-4.6 ↗

source model id
azure-huggingface/zai-org--glm-4.6@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
MIT
context length
202752
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    zai-org/GLM-4.6 ↗

    source model id
    azure-huggingface/zai-org--glm-4.6@2
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    license
    MIT
    context length
    202752
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      zai-org/GLM-4.6 ↗

      source model id
      azure-huggingface/zai-org--glm-4.6@3
      hosting
      foundry-managed-compute
      platforms
      • Microsoft Foundry
      license
      MIT
      context length
      202752
      architecture
      input_modalities
      • text
      output_modalities
      • text
      capabilities

        zai-org/GLM-4.6 ↗

        source model id
        azure-huggingface/zai-org--glm-4.6@4
        hosting
        foundry-managed-compute
        platforms
        • Microsoft Foundry
        license
        MIT
        context length
        202752
        architecture
        input_modalities
        • text
        output_modalities
        • text
        capabilities

          GLM 4.6 ↗

          source model id
          zai/glm-4.6
          hosting
          vercel-gateway
          platforms
          • Vercel AI Gateway
          context length
          200000
          max output tokens
          96000
          architecture
          input_modalities
          • text
          output_modalities
          • text
          capabilities
          • promptCaching
          • reasoning
          • structuredOutputs
          • toolCalling

          GLM-4.6 ↗

          source model id
          zai-org/GLM-4.6
          hosting
          siliconflow-hosted
          platforms
          • SiliconFlow
          max output tokens
          204800
          architecture
          input_modalities
          • text
          output_modalities
          • text
          capabilities
          • reasoning
          • structuredOutputs
          • toolCalling

          Source specification observations

          1–12 / 12

          azureFoundry ↗

          field
          context_length
          value
          202752
          normalized value
          202752
          scope
          source-model
          source id
          azureFoundry
          confidence
          1

          azureFoundry ↗

          field
          context_length
          value
          202752
          normalized value
          202752
          scope
          source-model
          source id
          azureFoundry
          confidence
          1

          azureFoundry ↗

          field
          context_length
          value
          202752
          normalized value
          202752
          scope
          source-model
          source id
          azureFoundry
          confidence
          1

          azureFoundry ↗

          field
          context_length
          value
          202752
          normalized value
          202752
          scope
          source-model
          source id
          azureFoundry
          confidence
          1

          openRouter ↗

          field
          context_length
          value
          204800
          normalized value
          204800
          scope
          source-model
          source id
          openRouter
          confidence
          1

          siliconFlow ↗

          field
          context_length
          value
          205K
          scope
          source-model
          source id
          siliconFlow
          confidence
          1

          vercelAIGatewayCatalog ↗

          field
          context_length
          value
          200000
          normalized value
          200000
          scope
          source-model
          source id
          vercelAIGatewayCatalog
          confidence
          1

          openRouter ↗

          field
          knowledge_cutoff
          reported field
          knowledge_cutoff
          value
          2025-03-31
          normalized value
          2025-03-31
          precision
          day
          scope
          source-model
          source id
          openRouter
          confidence
          1

          vercelAIGatewayCatalog ↗

          field
          knowledge_cutoff
          reported field
          knowledge_cutoff
          value
          2025-04
          normalized value
          2025-04
          precision
          month
          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

          siliconFlow ↗

          field
          max_output_tokens
          value
          205K
          scope
          source-model
          source id
          siliconFlow
          confidence
          1

          vercelAIGatewayCatalog ↗

          field
          max_output_tokens
          value
          96000
          normalized value
          96000
          scope
          source-model
          source id
          vercelAIGatewayCatalog
          confidence
          1

          Original sources

          1–20 / 21

          SiliconFlow · Model page ↗

          Hugging Face · Model reference ↗

          DeepInfra · Model page ↗

          Microsoft Foundry · Model page ↗

          Microsoft Foundry · Model page ↗

          Microsoft Foundry · Model page ↗

          Microsoft Foundry · Model page ↗

          OpenRouter · Model page ↗

          SiliconFlow · Playground ↗

          Vercel AI Gateway · Model page ↗

          Microsoft Foundry · Model documentation ↗

          SiliconFlow · API documentation ↗

          DeepInfra · Catalog ↗

          Hugging Face · Catalog ↗

          Microsoft Foundry · Catalog ↗

          OpenRouter · Catalog ↗

          OpenRouter · Catalog ↗

          SiliconFlow · Catalog ↗

          Vercel AI Gateway · Catalog ↗

          gorilla.cs.berkeley.edu · Catalog ↗

          Source links

          1–11 / 11

          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