Qwen: Qwen3 Next 80B A3B Instruct

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code…

qwen/qwen3-next-80b-a3b-instruct-2509

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual use, while remaining robust on alignment and formatting. Compared with prior Qwen3 instruct variants, it focuses on higher throughput and stability on ultra-long inputs and multi-turn dialogues, making it well-suited for RAG, tool use, and agentic workflows that require consistent final answers rather than visible chain-of-thought.

The model employs scaling-efficient training and decoding to improve parameter efficiency and inference speed, and has been validated on a broad set of public benchmarks where it reaches or approaches larger Qwen3 systems in several categories while outperforming earlier mid-sized baselines. It is best used as a general assistant, code helper, and long-context task solver in production settings where deterministic, instruction-following outputs are preferred.

Specifications & capabilities

Input
text
Output
text
Context window · tokens
262144
Published model ID
Qwen3-Next-80B-A3B-Instruct
Capabilities
structuredOutputs, toolCalling
Description source ↗

Evaluations

1–20 / 20

OpenRouter Benchmarks

71.324%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Alibaba
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
24
sample size
594
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
Alibaba
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-03T16:40:12.993Z
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
594
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7132433333333333
accuracy_std_dev
0.008837261503932612
cost_per_task_usd
0.00784910101010101
output_tokens_per_task
9968.289562289563
latency_seconds_per_task
79.02132323232324
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
qwen/qwen3-next-80b-a3b-instruct-2509
source model id
qwen/qwen3-next-80b-a3b-instruct-2509
Original result ↗

OpenRouter Benchmarks

44.222%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Alibaba
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
24
sample size
150
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
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
2026-10-03T16:10:49.378Z
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
150
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.44222233333333333
accuracy_std_dev
0.03281073296279061
cost_per_task_usd
0.026376873333333332
output_tokens_per_task
3752.213333333333
latency_seconds_per_task
59.34030666666666
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
qwen/qwen3-next-80b-a3b-instruct-2509
source model id
qwen/qwen3-next-80b-a3b-instruct-2509
Original result ↗

OpenRouter Benchmarks

44.556%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Parasail
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
25
sample size
150
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
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
2026-10-03T16:12:20.062Z
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
150
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.4455556666666666
accuracy_std_dev
0.03359162888114966
cost_per_task_usd
0.019044513333333336
output_tokens_per_task
3574.44
latency_seconds_per_task
90.75112
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
qwen/qwen3-next-80b-a3b-instruct-2509
source model id
qwen/qwen3-next-80b-a3b-instruct-2509
Original result ↗

OpenCompass LLM

81.3%

source id
openCompass
leaderboard name
MMLU-Pro
dimension
general
metric
MMLU-Pro
rank
27
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
MMLU-Pro
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Instruct
Original result ↗

OpenRouter Benchmarks

72.513%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Parasail
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
28
sample size
593
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
Parasail
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-03T16:43:17.105Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
593
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7251266559865094
accuracy_std_dev
0.005701732738582379
cost_per_task_usd
0.01145135581787521
output_tokens_per_task
10340.510961214166
latency_seconds_per_task
98.41320741989882
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
36
benchmark_evaluation
true
openrouter_permaslug
qwen/qwen3-next-80b-a3b-instruct-2509
source model id
qwen/qwen3-next-80b-a3b-instruct-2509
Original result ↗

OpenCompass LLM

74.1%

source id
openCompass
leaderboard name
GPQA-Diamond
dimension
general
metric
GPQA-Diamond
rank
30
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
GPQA-Diamond
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Instruct
Original result ↗

OpenCompass LLM

62.5%

source id
openCompass
leaderboard name
Average
dimension
general
metric
Average
rank
31
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
Average
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Instruct
Original result ↗

OpenCompass LLM

54.8%

source id
openCompass
leaderboard name
LiveCodeBenchV6
dimension
general
metric
LiveCodeBenchV6
rank
33
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
LiveCodeBenchV6
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Instruct
Original result ↗

OpenRouter Benchmarks

48%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Google
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
33
sample size
150
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
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Google
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-03T16:17:11.217Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
150
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.48
accuracy_std_dev
0.0282842712474619
cost_per_task_usd
0.0346484
output_tokens_per_task
3626.5266666666666
latency_seconds_per_task
39.535239999999995
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
36
benchmark_evaluation
true
openrouter_permaslug
qwen/qwen3-next-80b-a3b-instruct-2509
source model id
qwen/qwen3-next-80b-a3b-instruct-2509
Original result ↗

OpenRouter Benchmarks

69.473%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Google
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
34
sample size
594
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
Google
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-03T16:36:16.895Z
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
594
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.6947253333333333
accuracy_std_dev
0.03660940543388032
cost_per_task_usd
0.010800447811447811
output_tokens_per_task
8968.276094276094
latency_seconds_per_task
53.436715488215484
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
40
benchmark_evaluation
true
openrouter_permaslug
qwen/qwen3-next-80b-a3b-instruct-2509
source model id
qwen/qwen3-next-80b-a3b-instruct-2509
Original result ↗

OpenCompass LLM

87.6%

source id
openCompass
leaderboard name
IFEval
dimension
general
metric
IFEval
rank
35
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
IFEval
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Instruct
Original result ↗

OpenCompass LLM

69.2%

source id
openCompass
leaderboard name
AIME2025
dimension
general
metric
AIME2025
rank
36
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
AIME2025
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Instruct
Original result ↗

OpenCompass LLM

8%

source id
openCompass
leaderboard name
HLE
dimension
general
metric
HLE
rank
36
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
HLE
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Instruct
Original result ↗

OpenRouter Benchmarks

71.044%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Novita
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
45
sample size
594
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
Novita
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-03T16:46:22.205Z
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
594
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7104376666666667
accuracy_std_dev
0.004123715988711595
cost_per_task_usd
0.015477676767676767
output_tokens_per_task
10237.208754208754
latency_seconds_per_task
105.80374579124579
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
59
benchmark_evaluation
true
openrouter_permaslug
qwen/qwen3-next-80b-a3b-instruct-2509
source model id
qwen/qwen3-next-80b-a3b-instruct-2509
Original result ↗

OpenRouter Benchmarks

42.889%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Novita
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
46
sample size
150
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
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
2026-10-03T16:18:20.377Z
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
150
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.4288886666666667
accuracy_std_dev
0.011331263428624758
cost_per_task_usd
0.04006192
output_tokens_per_task
3385.233333333333
latency_seconds_per_task
171.57976000000002
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
qwen/qwen3-next-80b-a3b-instruct-2509
source model id
qwen/qwen3-next-80b-a3b-instruct-2509
Original result ↗

OpenRouter Benchmarks

70.48%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · DeepInfra
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
49
sample size
791
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
4
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
DeepInfra
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-08T22:40:37.311Z
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
791
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7048043337547408
accuracy_std_dev
0.0036369767922685555
cost_per_task_usd
0.010453273072060683
output_tokens_per_task
9436.553729456384
latency_seconds_per_task
132.2004804045512
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
qwen/qwen3-next-80b-a3b-instruct-2509
source model id
qwen/qwen3-next-80b-a3b-instruct-2509
Original result ↗

OpenRouter Benchmarks

45.333%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · DeepInfra
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
53
sample size
200
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
2026-10-08T22:47:27.753Z
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
200
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.45333349999999994
accuracy_std_dev
0.031001890623799048
cost_per_task_usd
0.021677975
output_tokens_per_task
3500.315
latency_seconds_per_task
234.04277
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
qwen/qwen3-next-80b-a3b-instruct-2509
source model id
qwen/qwen3-next-80b-a3b-instruct-2509
Original result ↗

OpenRouter Benchmarks

71.773%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · auto-routing
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
100
sample size
594
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
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-03T16:59:33.949Z
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
594
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7177330000000001
accuracy_std_dev
0.0028613344206273234
cost_per_task_usd
0.011208954545454548
output_tokens_per_task
10503.252525252525
latency_seconds_per_task
85.33255555555556
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
qwen/qwen3-next-80b-a3b-instruct-2509
source model id
qwen/qwen3-next-80b-a3b-instruct-2509
Original result ↗

OpenRouter Benchmarks

46.222%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · auto-routing
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
110
sample size
150
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
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
2026-10-03T16:13:56.619Z
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
150
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.4622220000000001
accuracy_std_dev
0.02266219999617573
cost_per_task_usd
0.023695320000000002
output_tokens_per_task
3751.38
latency_seconds_per_task
107.30777333333333
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
qwen/qwen3-next-80b-a3b-instruct-2509
source model id
qwen/qwen3-next-80b-a3b-instruct-2509
Original result ↗

Published prices

1–8 / 8

alibaba/qwen3-next-80b-a3b-instruct ↗

$0.09

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | alibaba/qwen3-next-80b-a3b-instruct
model_type
language
quantization
fp8
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

alibaba/qwen3-next-80b-a3b-instruct ↗

$1.10

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | alibaba/qwen3-next-80b-a3b-instruct
model_type
language
quantization
fp8
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

alibaba/qwen3-next-80b-a3b-instruct ↗

$0.15

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

alibaba/qwen3-next-80b-a3b-instruct ↗

$1.20

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

alibaba/qwen3-next-80b-a3b-instruct ↗

$0.15

Inference provider
vercelAIGatewayCatalog
Platform
vertex
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
vertex | alibaba/qwen3-next-80b-a3b-instruct
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

alibaba/qwen3-next-80b-a3b-instruct ↗

$1.20

Inference provider
vercelAIGatewayCatalog
Platform
vertex
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
vertex | alibaba/qwen3-next-80b-a3b-instruct
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–7 / 7

Qwen3 Next 80B A3B Instruct ↗

source model id
alibaba/qwen3-next-80b-a3b-instruct
hosting
vercel-gateway
platforms
  • Vercel AI Gateway
context length
262114
max output tokens
262114
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • structuredOutputs
  • toolCalling

Qwen/Qwen3-Next-80B-A3B-Instruct ↗

source model id
HuggingFace/qwen-qwen3-next-80b-a3b-instruct@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Qwen/Qwen3-Next-80B-A3B-Instruct ↗

    source model id
    HuggingFace/qwen-qwen3-next-80b-a3b-instruct@2
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    license
    apache-2.0
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      Qwen/Qwen3-Next-80B-A3B-Instruct ↗

      source model id
      HuggingFace/qwen-qwen3-next-80b-a3b-instruct@3
      hosting
      foundry-managed-compute
      platforms
      • Microsoft Foundry
      license
      apache-2.0
      architecture
      input_modalities
      • text
      output_modalities
      • text
      capabilities

        Qwen/Qwen3-Next-80B-A3B-Instruct ↗

        source model id
        publishers/hf-qwen/models/qwen3-next-80b-a3b-instruct@001
        hosting
        vertex-self-deployed
        platforms
        • Google Cloud Vertex AI
        architecture
        input_modalities
        • text
        output_modalities
        • text
        capabilities

          Qwen3-Next-80B-A3B-Instruct ↗

          source model id
          publishers/qwen/models/qwen3-next@qwen3-next-80b-a3b-instruct
          hosting
          vertex-self-deployed
          platforms
          • Google Cloud Vertex AI
          architecture
          input_modalities
          • text
          output_modalities
          • text
          capabilities

            Qwen3-Next-80B-A3B-Instruct ↗

            source model id
            Qwen/Qwen3-Next-80B-A3B-Instruct
            hosting
            siliconflow-hosted
            platforms
            • SiliconFlow
            max output tokens
            262144
            architecture
            input_modalities
            • text
            output_modalities
            • text
            capabilities
            • structuredOutputs
            • toolCalling

            Safety assessments

            1–1 / 1

            Foundation Model Transparency Index 2025 ↗

            26 / 100

            source id
            stanfordFMTI
            canonical model id
            qwen/qwen3-next-80b-a3b-instruct-2509
            taxonomy
            transparency
            hazard category
            transparency
            hazard name
            Organization transparency
            policy area
            Alibaba
            assessment type
            organization-level disclosure
            metric
            disclosure_score
            result label
            26 / 100
            sample size
            100
            updated at
            2026-11-09T18:08:05.227Z

            Source specification observations

            1–8 / 8

            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
            262114
            normalized value
            262114
            scope
            source-model
            source id
            vercelAIGatewayCatalog
            confidence
            1

            openRouter ↗

            field
            knowledge_cutoff
            reported field
            knowledge_cutoff
            value
            2025-09-30
            normalized value
            2025-09-30
            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
            16384
            normalized value
            16384
            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
            262114
            normalized value
            262114
            scope
            source-model
            source id
            vercelAIGatewayCatalog
            confidence
            1

            Original sources

            1–20 / 22

            SiliconFlow · Model page ↗

            Hugging Face · Model repository ↗

            Google Cloud · Model page ↗

            Google Cloud · 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 ↗

            GitHub · Catalog ↗

            GitHub · Catalog ↗

            Google Cloud · Catalog ↗

            Hugging Face · Catalog ↗

            Hugging Face · Catalog ↗

            Microsoft Foundry · Catalog ↗

            OpenRouter · Catalog ↗

            OpenRouter · 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