MoonshotAI: Kimi K3.1 Pro

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D creatio…

moonshotai/kimi-k3.1-pro-20261023

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D creation, financial research, and end-to-end agentic knowledge work, with native image and video understanding.

Specifications & capabilities

Input
text, image, video
Output
text
Context window · tokens
1048576
Published model ID
Kimi-K3.1-Pro
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Description source ↗

Evaluations

21–38 / 38

OpenRouter Benchmarks

91.919%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Relace
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
2
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
2026-11-05T00:00:09.895Z
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
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9191919999999999
cost_per_task_usd
0.062148696969696965
output_tokens_per_task
7696.424242424242
latency_seconds_per_task
92.71041414141415
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

78.667%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · DigitalOcean
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
2
sample size
50
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
2026-11-07T03:08:27.754Z
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
50
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.786667
cost_per_task_usd
0.37777382000000004
output_tokens_per_task
12248.68
latency_seconds_per_task
196.21666
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

77.333%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Nebius
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
2
sample size
50
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
Nebius
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-04T22:42:55.359Z
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
50
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.773333
cost_per_task_usd
0.2468412
output_tokens_per_task
10570.46
latency_seconds_per_task
828.35582
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

76%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Decart
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
2
sample size
50
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
Decart
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-11T15:19:13.582Z
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
50
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.76
cost_per_task_usd
0.14539668
output_tokens_per_task
10161.9
latency_seconds_per_task
189.2047
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

74.479%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · PrimaLabs
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
2
sample size
96
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
PrimaLabs
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-06T15:59:08.297Z
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
96
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7447914583333333
accuracy_std_dev
0.005435000000000023
cost_per_task_usd
0.13105378125
output_tokens_per_task
8026.104166666667
latency_seconds_per_task
273.8251666666667
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
2
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

91.583%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · DeepInfra
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
3
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
2026-11-05T06:03:33.391Z
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
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.915825
cost_per_task_usd
0.06562552525252525
output_tokens_per_task
6703.651515151515
latency_seconds_per_task
514.7786464646465
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

76.833%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Phala
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
Phala
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-05T18:26:07.849Z
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
0.7683335
accuracy_std_dev
0.018333500000000003
cost_per_task_usd
0.18849928
output_tokens_per_task
10339.12
latency_seconds_per_task
346.8684
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

76%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Morph
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
3
sample size
50
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
2026-11-05T06:25:26.737Z
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
50
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.76
cost_per_task_usd
0.27690942
output_tokens_per_task
10636.8
latency_seconds_per_task
230.4476
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

75.904%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · InferenceNet
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
3
sample size
249
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
5
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
InferenceNet
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-05T00:24:27.672Z
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
249
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7590360803212852
accuracy_std_dev
0.01520064937560236
cost_per_task_usd
0.21346128514056226
output_tokens_per_task
10222.072289156626
latency_seconds_per_task
312.6345903614458
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
10
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

74.667%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · AkashML
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
3
sample size
50
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
AkashML
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-05T06:21:39.264Z
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
50
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.746667
cost_per_task_usd
0.21601631999999998
output_tokens_per_task
10774.7
latency_seconds_per_task
312.89228
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
10
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

75.667%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Wafer
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
4
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
Wafer
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-05T21:56:52.017Z
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
0.7566669999999999
accuracy_std_dev
0.010000000000000009
cost_per_task_usd
0.17797051000000003
output_tokens_per_task
10362.94
latency_seconds_per_task
171.58738
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

73%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Modal
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
8
sample size
50
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
Modal
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-04T21:11:46.281Z
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
50
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.73
cost_per_task_usd
0.14279748
output_tokens_per_task
7981.12
latency_seconds_per_task
129.43532000000002
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

73%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Sail Research
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
9
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
2026-11-06T22:14:35.733Z
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
0.73
accuracy_std_dev
0.0033330000000000304
cost_per_task_usd
0.22321662
output_tokens_per_task
10411.9
latency_seconds_per_task
277.14238
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

73.333%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Together
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
13
sample size
50
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
2026-11-04T18:44:37.678Z
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
50
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7333330000000001
cost_per_task_usd
0.2865894
output_tokens_per_task
16191.68
latency_seconds_per_task
249.37806
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

73.333%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Parasail
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
14
sample size
50
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
Parasail
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-04T21:15:40.182Z
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
50
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7333330000000001
cost_per_task_usd
0.2484202
output_tokens_per_task
10608.24
latency_seconds_per_task
207.73362
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
28
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

74.667%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Alibaba
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
15
sample size
50
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
Alibaba
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-04T21:00:38.446Z
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
50
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.746667
cost_per_task_usd
0.33231256000000003
output_tokens_per_task
11123.54
latency_seconds_per_task
225.56704000000002
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
29
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

74.667%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · DeepInfra
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
22
sample size
50
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
2026-11-05T06:48:08.646Z
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
50
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.746667
cost_per_task_usd
0.22191687999999998
output_tokens_per_task
10495.84
latency_seconds_per_task
2285.67656
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

Published prices

1–20 / 67

moonshotai/kimi-k3.1-pro ↗

$0.20

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

moonshotai/kimi-k3.1-pro ↗

$0.20

Inference provider
vercelAIGatewayCatalog
Platform
alibaba
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
alibaba | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$2.00

Inference provider
vercelAIGatewayCatalog
Platform
alibaba
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
alibaba | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$10.00

Inference provider
vercelAIGatewayCatalog
Platform
alibaba
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
alibaba | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$0.20

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
baseten | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$2.00

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
baseten | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$10.00

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
baseten | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$0.20

Inference provider
vercelAIGatewayCatalog
Platform
boundless
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
boundless | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$1.70

Inference provider
vercelAIGatewayCatalog
Platform
boundless
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
boundless | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$8.50

Inference provider
vercelAIGatewayCatalog
Platform
boundless
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
boundless | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$0.19

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$1.90

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$9.50

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$0.20

Inference provider
vercelAIGatewayCatalog
Platform
digitalocean
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
digitalocean | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$2.00

Inference provider
vercelAIGatewayCatalog
Platform
digitalocean
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
digitalocean | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–2 / 2

Kimi K3.1 Pro ↗

source model id
moonshotai/kimi-k3.1-pro
hosting
vercel-gateway
platforms
  • Vercel AI Gateway
context length
1000000
max output tokens
262144
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • promptCaching
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput
regions
  • us

kimi-k3.1-pro ↗

source model id
moonshotai/kimi-k3_1-pro
hosting
nvidia-catalog
platforms
  • NVIDIA Build / NIM
context length
1048576
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • toolCalling
  • structuredOutputs
  • reasoning

Source specification observations

1–7 / 7

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

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

openRouter ↗

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

vercelAIGatewayCatalog ↗

field
max_output_tokens
value
262144
normalized value
262144
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

Original sources

1–12 / 12

Hugging Face · Model reference ↗

NVIDIA · Model page ↗

OpenRouter · Model page ↗

OpenRouter · Model page ↗

Vercel AI Gateway · Model page ↗

NVIDIA · Documentation ↗

Epoch AI · Catalog ↗

Hugging Face · Catalog ↗

NVIDIA · Catalog ↗

OpenRouter · Catalog ↗

OpenRouter · Catalog ↗

Vercel AI Gateway · Catalog ↗

Source links

1–8 / 8

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