MoonshotAI: Kimi K2.6

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding task…

moonshotai/kimi-k2.6-20260420

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.

Specifications & capabilities

Input
text, image
Output
text
Context window · tokens
262144
Knowledge cutoff
2025-01
Published model ID
Kimi-K2.6
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput
Description source ↗

Evaluations

41–59 / 59

OpenCompass LLM

74.5%

source id
openCompass
leaderboard name
Comprehensive_Coding_Ability
dimension
general
metric
Comprehensive_Coding_Ability
rank
14
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
CodeTable
catalog
closed
snapshot
month
26-07
fileName
assets/llm-rank/llm-data-v2.26-07.20260824.json
updateTime
2026-08-24
columnFileName
assets/llm-rank/llm-column-v2.26-07.20260824.json
metric_kind
Comprehensive_Coding_Ability
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
1-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
15
benchmark_evaluation
true
source model id
Kimi-K2.6 (high)
Original result ↗

OpenCompass LLM

74.5%

source id
openCompass
leaderboard name
Code
dimension
general
metric
Code
rank
14
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
closed
snapshot
month
26-07
fileName
assets/llm-rank/llm-data-v2.26-07.20260824.json
updateTime
2026-08-24
columnFileName
assets/llm-rank/llm-column-v2.26-07.20260824.json
metric_kind
Code
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
1-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
15
benchmark_evaluation
true
source model id
Kimi-K2.6 (high)
Original result ↗

OpenCompass LLM

74.5%

source id
openCompass
leaderboard name
Average
dimension
general
metric
Average
rank
14
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
CodeTable
catalog
closed
snapshot
month
26-07
fileName
assets/llm-rank/llm-data-v2.26-07.20260824.json
updateTime
2026-08-24
columnFileName
assets/llm-rank/llm-column-v2.26-07.20260824.json
metric_kind
Average
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
1-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
15
benchmark_evaluation
true
source model id
Kimi-K2.6 (high)
Original result ↗

OpenRouter Benchmarks

73.444%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · SiliconFlow
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
14
sample size
300
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
SiliconFlow
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-24T22:27:21.158Z
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
300
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7344446666666666
accuracy_std_dev
0.03183677894965017
cost_per_task_usd
0.07159142333333333
output_tokens_per_task
11458.973333333333
latency_seconds_per_task
344.98860666666667
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-k2.6-20260420
source model id
moonshotai/kimi-k2.6-20260420
Original result ↗

OpenRouter Benchmarks

72.8%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Venice
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
15
sample size
250
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
Venice
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-24T23:08:37.435Z
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
250
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.728
accuracy_std_dev
0.03194425700497665
cost_per_task_usd
0.080962124
output_tokens_per_task
12180.928
latency_seconds_per_task
531.0362
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
38
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k2.6-20260420
source model id
moonshotai/kimi-k2.6-20260420
Original result ↗

OpenRouter Benchmarks

72.833%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Parasail
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
16
sample size
300
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
Parasail
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T20:16:51.242Z
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
300
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7283333333333334
accuracy_std_dev
0.03857423338908441
cost_per_task_usd
0.07535822
output_tokens_per_task
11190.87
latency_seconds_per_task
168.34759666666667
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-k2.6-20260420
source model id
moonshotai/kimi-k2.6-20260420
Original result ↗

OpenRouter Benchmarks

71.667%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · StreamLake
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
16
sample size
400
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
tau_bench_verified_airline
name
tau2-bench Verified Airline
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
2026-10-31T19:48:30.443Z
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
400
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.716666625
accuracy_std_dev
0.029627375668195347
cost_per_task_usd
0.0693026925
output_tokens_per_task
12604.555
latency_seconds_per_task
283.497055
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
25
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k2.6-20260420
source model id
moonshotai/kimi-k2.6-20260420
Original result ↗

OpenRouter Benchmarks

71.333%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · GMICloud
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
17
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
GMICloud
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-08-29T17:18:09.782Z
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
0.713333
cost_per_task_usd
0.09868048
output_tokens_per_task
11794.24
latency_seconds_per_task
318.461
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-k2.6-20260420
source model id
moonshotai/kimi-k2.6-20260420
Original result ↗

OpenRouter Benchmarks

73.429%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Novita
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
19
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
Novita
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T20:07:04.555Z
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
0.7342857142857143
accuracy_std_dev
0.03331958219903675
cost_per_task_usd
0.09951040285714285
output_tokens_per_task
12551.72
latency_seconds_per_task
257.63584285714285
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
moonshotai/kimi-k2.6-20260420
source model id
moonshotai/kimi-k2.6-20260420
Original result ↗

OpenRouter Benchmarks

81.938%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · AtlasCloud
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
20
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
2026-10-31T16:08:08.537Z
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
0.8193842857142857
accuracy_std_dev
0.05010024752352396
cost_per_task_usd
0.20815405194805192
output_tokens_per_task
51956.655122655124
latency_seconds_per_task
879.9471565656565
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
moonshotai/kimi-k2.6-20260420
source model id
moonshotai/kimi-k2.6-20260420
Original result ↗

OpenRouter Benchmarks

70.933%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · AtlasCloud
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
20
sample size
250
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
AtlasCloud
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-17T19:18:15.219Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
250
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7093334
accuracy_std_dev
0.07236922366199598
cost_per_task_usd
0.10543298799999999
output_tokens_per_task
11270.708
latency_seconds_per_task
199.005244
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-k2.6-20260420
source model id
moonshotai/kimi-k2.6-20260420
Original result ↗

OpenRouter Benchmarks

80.011%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Venice
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
22
sample size
582
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
3
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
2026-10-24T16:13:05.627Z
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
582
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8001147113402061
accuracy_std_dev
0.1242203500272354
cost_per_task_usd
0.11411094845360827
output_tokens_per_task
38030.19243986254
latency_seconds_per_task
1146.5036958762887
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
moonshotai/kimi-k2.6-20260420
source model id
moonshotai/kimi-k2.6-20260420
Original result ↗

OpenRouter Benchmarks

73.79%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · DeepInfra
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
29
sample size
248
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
DeepInfra
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-24T19:42:30.512Z
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
248
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7379031612903226
accuracy_std_dev
0.033855790905545226
cost_per_task_usd
0.06981228629032259
output_tokens_per_task
10842.524193548386
latency_seconds_per_task
509.43004435483874
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-k2.6-20260420
source model id
moonshotai/kimi-k2.6-20260420
Original result ↗

OpenRouter Benchmarks

73.654%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · DeepInfra
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
44
sample size
935
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
DeepInfra
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T16:05:14.699Z
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
935
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7365419711229947
accuracy_std_dev
0.1044922112691581
cost_per_task_usd
0.09201655614973261
output_tokens_per_task
26199.03101604278
latency_seconds_per_task
1267.1319229946523
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-k2.6-20260420
source model id
moonshotai/kimi-k2.6-20260420
Original result ↗

OpenRouter Benchmarks

86.715%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · auto-routing
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
46
sample size
1385
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
2026-10-31T16:11:41.349Z
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
1385
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.867147968231047
accuracy_std_dev
0.04215195953321502
cost_per_task_usd
0.16483890613718413
output_tokens_per_task
56075.11624548736
latency_seconds_per_task
954.9615436823105
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
moonshotai/kimi-k2.6-20260420
source model id
moonshotai/kimi-k2.6-20260420
Original result ↗

OpenRouter Benchmarks

73.143%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · auto-routing
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
49
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
2026-10-31T20:18:31.003Z
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
0.7314284285714286
accuracy_std_dev
0.019424805892445475
cost_per_task_usd
0.06280418
output_tokens_per_task
12506.968571428572
latency_seconds_per_task
232.82265142857145
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
moonshotai/kimi-k2.6-20260420
source model id
moonshotai/kimi-k2.6-20260420
Original result ↗

Published prices

1–17 / 17

@cf/moonshotai/kimi-k2.6 ↗

$0.16

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

@cf/moonshotai/kimi-k2.6 ↗

$4.00

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

moonshotai/kimi-k2.6 ↗

$0.15

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

moonshotai/kimi-k2.6 ↗

$0.65

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

moonshotai/kimi-k2.6 ↗

$3.41

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

moonshotai/Kimi-K2.6 ↗

$0.14

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

moonshotai/Kimi-K2.6 ↗

$0.77

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

moonshotai/Kimi-K2.6 ↗

$3.40

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

moonshotai/kimi-k2.6 ↗

$0.16

Inference provider
vercelAIGatewayCatalog
Platform
moonshotai
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
moonshotai | moonshotai/kimi-k2.6
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k2.6 ↗

$0.95

Inference provider
vercelAIGatewayCatalog
Platform
moonshotai
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
moonshotai | moonshotai/kimi-k2.6
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k2.6 ↗

$4.00

Inference provider
vercelAIGatewayCatalog
Platform
moonshotai
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
moonshotai | moonshotai/kimi-k2.6
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k2.6 ↗

$0.16

Inference provider
vercelAIGatewayCatalog
Platform
novita
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
novita | moonshotai/kimi-k2.6
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k2.6 ↗

$0.80

Inference provider
vercelAIGatewayCatalog
Platform
novita
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
novita | moonshotai/kimi-k2.6
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k2.6 ↗

$3.40

Inference provider
vercelAIGatewayCatalog
Platform
novita
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
novita | moonshotai/kimi-k2.6
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k2.6 ↗

$0.16

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

moonshotai/kimi-k2.6 ↗

$0.95

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

moonshotai/kimi-k2.6 ↗

$4.00

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

Provider specifications & access

1–5 / 5

kimi-k2.6 ↗

source model id
@cf/moonshotai/kimi-k2.6
hosting
cloudflare-hosted
platforms
  • Cloudflare Workers AI
context length
262144
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • toolCalling

moonshotai/kimi-k2.6 ↗

source model id
moonshotai/kimi-k2.6
hosting
nvidia-inference-listed
platforms
  • NVIDIA inference catalog
architecture
input_modalities
    output_modalities
      capabilities
        availability
        Listed by inference API; runtime availability unverified

        Kimi K2.6 ↗

        source model id
        moonshotai/kimi-k2.6
        hosting
        vercel-gateway
        platforms
        • Vercel AI Gateway
        context length
        262000
        max output tokens
        262000
        architecture
        input_modalities
        • text
        • image
        • video
        output_modalities
        • text
        capabilities
        • promptCaching
        • reasoning
        • structuredOutputs
        • toolCalling
        • videoInput
        • visionInput

        Kimi-K2.6 ↗

        source model id
        moonshotai/Kimi-K2.6
        hosting
        siliconflow-hosted
        platforms
        • SiliconFlow
        max output tokens
        262144
        architecture
        input_modalities
        • text
        • image
        output_modalities
        • text
        capabilities
        • promptCaching
        • reasoning
        • structuredOutputs
        • toolCalling

        Kimi-K2.6 ↗

        source model id
        publishers/moonshotai/models/kimi-k2-6@kimi-k2.6
        hosting
        vertex-self-deployed
        platforms
        • Google Cloud Vertex AI
        architecture
        input_modalities
        • text
        output_modalities
        • text
        capabilities

          Source specification observations

          1–7 / 7

          openRouter ↗

          field
          context_length
          value
          262144
          normalized value
          262144
          scope
          source-model
          source id
          openRouter
          confidence
          1

          siliconFlow ↗

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

          vercelAIGatewayCatalog ↗

          field
          context_length
          value
          262000
          normalized value
          262000
          scope
          source-model
          source id
          vercelAIGatewayCatalog
          confidence
          1

          vercelAIGatewayCatalog ↗

          field
          knowledge_cutoff
          reported field
          knowledge_cutoff
          value
          2025-01
          normalized value
          2025-01
          precision
          month
          scope
          source-model
          source id
          vercelAIGatewayCatalog
          confidence
          1

          openRouter ↗

          field
          max_output_tokens
          value
          235929
          normalized value
          235929
          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
          262000
          normalized value
          262000
          scope
          source-model
          source id
          vercelAIGatewayCatalog
          confidence
          1

          Original sources

          1–20 / 20

          SiliconFlow · Model page ↗

          www.kimi.com · Model reference ↗

          Hugging Face · Model repository ↗

          Cloudflare AI · Model page ↗

          Google Cloud · Model page ↗

          OpenRouter · Model page ↗

          SiliconFlow · Playground ↗

          Vercel AI Gateway · Model page ↗

          SiliconFlow · API documentation ↗

          GitHub · Source snapshot ↗

          NVIDIA · Catalog ↗

          Cloudflare AI · Catalog ↗

          Epoch AI · Catalog ↗

          Google Cloud · Catalog ↗

          Hugging Face · Catalog ↗

          Hugging Face · Catalog ↗

          OpenRouter · Catalog ↗

          OpenRouter · Catalog ↗

          SiliconFlow · Catalog ↗

          Vercel AI Gateway · Catalog ↗

          Source links

          1–12 / 12

          Explore more models

          Models

          Loading
          EVIDENCE / COMPARISON

          Benchmarks

          Explore every benchmark

          Loading

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

          Install TensorTrace