RankingEffort benchmarks

NVIDIA Nemotron 3 Ultra effort benchmarks

Compare measured Low, Medium, High and other settings. Every number keeps its source.

Model

NVIDIA Nemotron 3 Ultra

27 measured results · 2 reported effort labels · 27 benchmark/harness combinations. Model evidence and sources →

Capability score evidence

NVIDIA Nemotron 3 Ultra · Reasoning: 16.2 overall comparison score. Meets the overall evidence requirements.

Which sources carry the weight?

Artificial Analysis · 100.0% direct comparison weight · independent

These shares describe the comparisons entering the fit, not fractions of the final score.

How sensitive is this score?

Remove one evaluator or family and refit the graph against the same overall panel. Values use the matching dataset audited 2026-09-12. These are sensitivity checks, not confidence intervals; ranking eligibility may also change.

Removed evidence	Recomputed score	Change
Artificial Analysis	Comparison path lost	—
ARC Prize	18.7	+2.5
Datacurve	14.1	-2.2
LiveCodeBench	16.1	-0.1
Scale	17.6	+1.3
Terminal-Bench	16.2	+0.0
Cognition	16.8	+0.5
LiveBench	16.5	+0.3
SWE-rebench	16.6	+0.4
Epoch AI	16.4	+0.2
Vals AI	15.8	-0.4
Provider reports · Anthropic	16.2	+0.0
Provider reports · Moonshot AI	16.2	-0.0
Provider reports · Meta	16.2	-0.0
Provider reports · Mistral	16.2	+0.0
All provider reports	16.2	-0.0

Every benchmark family

Removed evidence	Recomputed score	Change
arc-agi	18.6	+2.4
deepswe	14.1	-2.1
ifbench	14.9	-1.3
analyst-agent	17.1	+0.9
scicode	17.1	+0.8
automationbench	17.1	+0.8
aa-lcr	15.5	-0.8
mmmu-pro	17.0	+0.7
gpqa	15.6	-0.7
omniscience	16.9	+0.6
gdp-pdf	16.8	+0.6
epoch-game-puzzles	15.7	-0.6
enterprise-ops	16.8	+0.6
frontiercode	16.8	+0.5
simpleqa	16.7	+0.5
harvey	15.8	-0.4
briefcase	15.9	-0.4
swe-rebench	16.6	+0.4
gdpval	15.9	-0.4
mmlu-pro	16.6	+0.3
hle	16.5	+0.2
critpt	16.0	-0.2
multi-swe-bench	16.0	-0.2
livebench-instructions	16.4	+0.2
livebench-language	16.4	+0.2
apex-agents	16.4	+0.2
swe-atlas-qna	16.1	-0.1
terminal-bench	16.1	-0.1
frontiermath	16.4	+0.1
arc-agi-3	16.1	-0.1
livebench-coding	16.1	-0.1
vibe-code	16.2	-0.1
livebench-reasoning	16.2	-0.1
vals-finance-agent	16.2	-0.1
livecodebench	16.2	-0.1
vals-legal-research	16.2	-0.1
swe-atlas-test-writing	16.2	-0.1
itbench	16.2	-0.0
vals-code-migration	16.2	-0.0
gmmlu	16.3	+0.0
math500	16.3	+0.0
tau-bench	16.2	-0.0
livebench-data	16.3	+0.0
swe-atlas-refactoring	16.2	-0.0
livebench-math	16.3	+0.0
vals-excel-modeling	16.2	-0.0
enigma-eval	16.3	+0.0
swe-bench-pro	16.2	+0.0
aime	16.2	-0.0

What evidence is missing from the fit?

Across all collected settings for this model: 72 observations, 20 contributing, 0 matched without graph weight and 52 excluded. Counts do not establish rank eligibility.

1 · Benchmark family or source protocol has not been reviewed
2 · The evaluator reports no named effort control. This does not identify a non-reasoning configuration.
4 · Effort is not identified
19 · Supporting evidence outside the reviewed capability core
13 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
7 · No matched, identified effort unit; duplicates and unnamed comparators do not add evidence
6 · Legacy self-report lacks a reviewed comparison configuration

Inspect every observation and exclusion →

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

ANVIDIA Nemotron 3 Ultra · Reasoning4 of 7 capabilities supported

Gaps are unknown, not zero. Hollow points are preliminary.

Agentic
A16.4Supported
Hard reasoning
A25.5Supported
Coding
A14.1Supported
Human pref
Unknown
Knowledge
A24.1Supported
Multimodal
Unknown
Long context
A38.4Preliminary

Each profile belongs to the named configuration. Capability scores use a shared panel for all axes, distinct from the overall ranking panel; they are not accuracy percentages or direct head-to-head wins.

Compare this configuration →Explore the model evidence profile →

These are published benchmark scores. Supported effort estimates also appear on the Capability leaderboard. Results from different harnesses occupy different rows. Missing cells stay unknown; no scores are copied between effort levels.

Benchmark / source	Reasoning	Unspecified
AA-AnalystAgentArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of tasks solved on all 5 of 5 attempts · 80 tasks, 5 attempts per task · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	6.25% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
AA-Briefcase EloArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Briefcase is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-09-12.	878.22 Elo Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
AA-LCR v1.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	79.33% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
AutomationBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of task objectives completed with no guardrail violations · Higher is better · Benchmark developed by Zapier · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	2.99% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
CritPtArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Argonne and UIUC, with contributions from 60+ researchers globally · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	3.14% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
EnterpriseOps-Gym-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Overall task success rate across all eight enterprise domains (oracle tool mode) · Benchmark developed by ServiceNow Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	28.89% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
GDP.pdf: All-passArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of attempts where every atomic criterion passed · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	5% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
GDPval-AA v2 LeaderboardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Elo rating for performance on real-world work tasks · Anchored to a human baseline of 1,000 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-09-12.	1,090.88 Elo Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
GPQA DiamondArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	86.67% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
Harvey LAB-AA: Criterion Pass RateArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of atomic pass/fail rubric criteria the deliverables satisfy, graded by a single LLM judge · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	81.72% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
Humanity's Last ExamArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	28.41% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
IFBenchArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	81.36% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
MLCR-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of tasks judged accurate, complete, and concise · Expert + compound (hard) sets · Benchmark developed by Wisedocs · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	11.11% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
AA-Omniscience IndexArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis Unit: index. Source collected 2026-09-12.	-0.4 Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
AA-Omniscience AccuracyArtificial Analysis · 6000 questions; 1 attempt; correct-answer share; GPT-5.6 Luna medium grader Benchmark details AA-Omniscience Accuracy (higher is better) measures the proportion of correctly answered questions out of all questions, regardless of whether the model chooses to answer · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	22.58% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
SciCodeArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	40.28% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
𝜏²-Bench TelecomArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	83.33% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
𝜏³-BankingArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Sierra Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	14.23% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
Terminal-Bench HardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	36.36% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
Terminal-Bench v2.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by the Laude Institute and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	53.93% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
Terminal-Bench v4.0Artificial Analysis · mini-SWE-agent v2.4.6; 66 tasks; pass@1 averaged over 3 repeats; 500 steps; task timeout up to 8 hours Benchmark details Benchmark developed by the Laude Institute, Stanford, and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	0.51% Reported settings Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b	Not reported
FrontierCode 1.1 · extended-chiselCognition · chisel Benchmark details FrontierCode 1.1; chisel. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-09-12.	Not reported	27.21% Reported settings FrontierCode 1.1; extended; 150 tasks; chisel; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0013 The evaluator reports no named effort control. This does not identify a non-reasoning configuration. Source label needs review
FrontierCode 1.1 · main-chiselCognition · chisel Benchmark details FrontierCode 1.1; chisel. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-09-12.	Not reported	13.61% Reported settings FrontierCode 1.1; main; 100 tasks; chisel; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002 The evaluator reports no named effort control. This does not identify a non-reasoning configuration. Source label needs review
Epoch · Chess Puzzles · v1.1.6Epoch AI · Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	12% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=nemotron-3-ultra; run=26q7yB8XHAcmxWgEMFPMHP; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · GPQA diamond · v1.0.11Epoch AI · Epoch AI Inspect; task 1.0.11; scorer choice Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	85.35% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=nemotron-3-ultra; run=bpZy8tAbh7UV6A6U7XZtBg; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · Mystery Game Puzzles · v1.0.4 · Tool submissionEpoch AI · Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	20% Reported settings Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=nemotron-3-ultra; run=U8H8juE3Ko83jsR6TRntbh; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · OTIS Mock AIME 2024-2025 · v1.1.6Epoch AI · Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	86.67% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=nemotron-3-ultra; run=WYTWr3Xk4qxymhMsm7vRQ2; mean accuracy; https://epoch.ai/data/benchmarks.csv

What these comparisons mean

Each source reports its own effort labels. Matching labels do not establish equal compute budgets or identical fallback behavior. Open Reported settings to inspect the exact model name, agent and task coverage. Multiple results at one level remain visible rather than selecting the best. Source-reported None or Non-reasoning labels are not treated as evidence that an API supports those settings.

These measurements use their own dated source collection. The leaderboard fits identified configurations jointly; it contains no pooled model ratings. Explicit thinking budgets are separate configurations. Read the methodology.

Download all effort benchmark results · 7,424 results across 240 models · Collected 2026-09-12

NVIDIA Nemotron 3 Ultra effort benchmarks