NVIDIA: Nemotron 3 Nano 30B A3B

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

nvidia/nemotron-3-nano-30b-a3b

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

Specifications & capabilities

Input
text
Output
text
Context window · tokens
262144
Published model ID
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Evaluations

1–20 / 90

OpenRouter Benchmarks

47.5%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Crusoe
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
13
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
Crusoe
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-03T16:14:03.053Z
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
0.475
accuracy_std_dev
0.01960262643116988
cost_per_task_usd
0.029653983333333335
output_tokens_per_task
63168.53
latency_seconds_per_task
359.8295333333333
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
nvidia/nemotron-3-nano-30b-a3b
source model id
nvidia/nemotron-3-nano-30b-a3b
Original result ↗

OpenRouter Benchmarks

63.312%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Crusoe
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
14
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
Crusoe
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-03T17:08:02.072Z
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
0.633117
accuracy_std_dev
0.010839761238804363
cost_per_task_usd
0.01982476406926407
output_tokens_per_task
99141.9025974026
latency_seconds_per_task
532.40284992785
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
15
benchmark_evaluation
true
openrouter_permaslug
nvidia/nemotron-3-nano-30b-a3b
source model id
nvidia/nemotron-3-nano-30b-a3b
Original result ↗

OpenRouter Benchmarks

48.851%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Nebius
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
18
sample size
348
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
Nebius
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-23T09:26:25.528Z
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
348
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.48850570114942526
accuracy_std_dev
0.017439968302957548
cost_per_task_usd
0.031982068965517245
output_tokens_per_task
59401.63505747126
latency_seconds_per_task
642.915867816092
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
nvidia/nemotron-3-nano-30b-a3b
source model id
nvidia/nemotron-3-nano-30b-a3b
Original result ↗

OpenRouter Benchmarks

62.71%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Nebius
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
21
sample size
1584
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
8
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Nebius
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-23T09:03:34.804Z
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
1584
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.627104375
accuracy_std_dev
0.008333089267155095
cost_per_task_usd
0.024497946969696968
output_tokens_per_task
101874.34027777778
latency_seconds_per_task
1060.4091414141415
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
nvidia/nemotron-3-nano-30b-a3b
source model id
nvidia/nemotron-3-nano-30b-a3b
Original result ↗

OpenRouter Benchmarks

49.2%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · DeepInfra
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
48
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
DeepInfra
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-09-26T16:00:25.689Z
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
0.492
accuracy_std_dev
0.02578540500360622
cost_per_task_usd
0.026663912
output_tokens_per_task
52711.976
latency_seconds_per_task
680.6958880000001
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
nvidia/nemotron-3-nano-30b-a3b
source model id
nvidia/nemotron-3-nano-30b-a3b
Original result ↗

OpenRouter Benchmarks

68.04%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · DeepInfra
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
51
sample size
1153
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
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
2026-09-26T16:34:21.219Z
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
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1153
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.6803991483087598
accuracy_std_dev
0.010339641763888907
cost_per_task_usd
0.018036671292281006
output_tokens_per_task
89989.56808326105
latency_seconds_per_task
929.5522064180399
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
nvidia/nemotron-3-nano-30b-a3b
source model id
nvidia/nemotron-3-nano-30b-a3b
Original result ↗

OpenRouter Benchmarks

59.562%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Novita
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
52
sample size
1370
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
Novita
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-03T17:04:03.802Z
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
1370
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.595620394160584
accuracy_std_dev
0.009567520605183589
cost_per_task_usd
0.009091688321167881
output_tokens_per_task
45264.08613138686
latency_seconds_per_task
479.8202708029197
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
nvidia/nemotron-3-nano-30b-a3b
source model id
nvidia/nemotron-3-nano-30b-a3b
Original result ↗

OpenRouter Benchmarks

51.778%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · auto-routing
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
104
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
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-03T16:09:19.689Z
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
0.517778
accuracy_std_dev
0.027125670043951618
cost_per_task_usd
0.02834386
output_tokens_per_task
58278.28333333333
latency_seconds_per_task
441.85892333333334
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
nvidia/nemotron-3-nano-30b-a3b
source model id
nvidia/nemotron-3-nano-30b-a3b
Original result ↗

OpenRouter Benchmarks

63.228%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · auto-routing
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
114
sample size
1386
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
7
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-03T17:40:51.448Z
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
0.6322752857142858
accuracy_std_dev
0.02198430561439089
cost_per_task_usd
0.018390331168831167
output_tokens_per_task
89392.03174603175
latency_seconds_per_task
674.7199083694084
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
nvidia/nemotron-3-nano-30b-a3b
source model id
nvidia/nemotron-3-nano-30b-a3b
Original result ↗

LMArena

1,395.059

source id
lmarena
leaderboard name
LMArena Text Factuality Chinese
dimension
factuality
metric
Arena rating
rank
120
sample size
706
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
confidence lower
1371.2285433695051
confidence upper
1418.8893459364558
Original result ↗

LMArena

1,376.616

source id
lmarena
leaderboard name
LMArena Text Factuality Math
dimension
factuality
metric
Arena rating
rank
120
sample size
611
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
confidence lower
1354.2274574295877
confidence upper
1399.0046456521395
Original result ↗

LMArena

1,353.206

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Legal And Government
dimension
factuality
metric
Arena rating
rank
130
sample size
700
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
confidence lower
1329.5090634437895
confidence upper
1376.901947460252
Original result ↗

LMArena

1,334.933

source id
lmarena
leaderboard name
LMArena Text Factuality Russian
dimension
factuality
metric
Arena rating
rank
141
sample size
1227
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
confidence lower
1316.9379936203277
confidence upper
1352.9277865319875
Original result ↗

LMArena

1,374.21

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Life And Physical And Social Science
dimension
factuality
metric
Arena rating
rank
151
sample size
1630
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
confidence lower
1359.554249566649
confidence upper
1388.8656180178832
Original result ↗

LMArena

1,300.668

source id
lmarena
leaderboard name
LMArena Text Factuality Creative Writing
dimension
factuality
metric
Arena rating
rank
155
sample size
1449
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
confidence lower
1286.103865678681
confidence upper
1315.2318473473595
Original result ↗

LMArena

1,365.77

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Business And Management And Financial Operations
dimension
factuality
metric
Arena rating
rank
158
sample size
1915
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
confidence lower
1352.7364698534145
confidence upper
1378.8030385004697
Original result ↗

LMArena

1,341.981

source id
lmarena
leaderboard name
LMArena Text Factuality Multi Turn
dimension
factuality
metric
Arena rating
rank
158
sample size
1708
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
confidence lower
1327.9304101936837
confidence upper
1356.0325044629712
Original result ↗

LMArena

1,396.202

source id
lmarena
leaderboard name
LMArena Text French
dimension
general
metric
Arena rating
rank
159
sample size
364
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
confidence lower
1365.7997206164448
confidence upper
1426.604121308122
Original result ↗

LMArena

1,322.021

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Entertainment And Sports And Media
dimension
factuality
metric
Arena rating
rank
159
sample size
1865
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
confidence lower
1308.9490615389866
confidence upper
1335.0920651482322
Original result ↗

LMArena

1,418.097

source id
lmarena
leaderboard name
LMArena Text Factuality Coding
dimension
factuality
metric
Arena rating
rank
163
sample size
2116
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
confidence lower
1405.648354591556
confidence upper
1430.5453584308473
Original result ↗

Published prices

1–5 / 5

Provider specifications & access

1–3 / 3

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 ↗

source model id
HuggingFace/nvidia-nvidia-nemotron-3-nano-30b-a3b-bf16@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
nvidia-open-model-license
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 ↗

    source model id
    publishers/hf-nvidia/models/nvidia-nemotron-3-nano-30b-a3b-bf16@001
    hosting
    vertex-self-deployed
    platforms
    • Google Cloud Vertex AI
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 ↗

      source model id
      publishers/nvidia/models/nemotron-v3@nemotron-3-nano-30b-a3b-bf16
      hosting
      vertex-self-deployed
      platforms
      • Google Cloud Vertex AI
      architecture
      input_modalities
      • text
      output_modalities
      • text
      capabilities

        Source specification observations

        1–2 / 2

        openRouter ↗

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

        openRouter ↗

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

        Original sources

        1–18 / 18

        NVIDIA · Model reference ↗

        Hugging Face · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 ↗

        DeepInfra · Model page ↗

        Google Cloud · Model page ↗

        Google Cloud · Model page ↗

        Microsoft Foundry · Model page ↗

        OpenRouter · Model page ↗

        Microsoft Foundry · Model documentation ↗

        arXiv · Paper · 2512.20848 ↗

        arXiv · Paper · 2512.20856 ↗

        DeepInfra · Catalog ↗

        Epoch AI · Catalog ↗

        Google Cloud · Catalog ↗

        Hugging Face · Catalog ↗

        LMArena · Catalog ↗

        Microsoft Foundry · Catalog ↗

        OpenRouter · Catalog ↗

        OpenRouter · Catalog ↗

        Source links

        1–9 / 9

        Hugging Face model card

        1–1 / 1

        Explore more models

        Models

        Loading
        EVIDENCE / COMPARISON

        Benchmarks

        Explore every benchmark

        Loading

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

        Install TensorTrace