RankingEffort benchmarks

NVIDIA Nemotron 3 Ultra · Reasoning

Compare models

29 measured results · 2 effort settings · 29 benchmark/harness combinations

Model evidence and sources →

Change model

Model

Current configurationSources

Compare with

Choose a second model and its effort to see both profiles and benchmark differences below.

Compare withModel and configuration

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

ANVIDIA Nemotron 3 Ultra · Reasoning3 of 7 capabilities supported

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

Agentic
A15.5Supported
Hard reasoning
A25.6Supported
Coding
A21.7Preliminary
Human pref
Unknown
Knowledge
A21.2Supported
Multimodal
Unknown
Long context
A37.0Preliminary

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.

Capability score evidence

NVIDIA Nemotron 3 Ultra · Reasoning: 10.4 overall comparison score. Meets the overall evidence requirements.

5 areas measured. The available task mix affects this estimate; missing areas remain unknown.

Which sources carry the weight?

Artificial Analysis · 100.0% direct comparison weight · independent of the model provider

Which benchmark families carry the weight?

IFBench · 8.3% direct comparison weight
Humanity’s Last Exam · 8.1% direct comparison weight
GPQA · 8.1% direct comparison weight
Critpt · 8.1% direct comparison weight
omniscience · 8.1% direct comparison weight
Other families (9) · 59.3% direct comparison weight

These shares describe direct comparison weight, not fractions of the final score or confidence. Source balancing does not give every family equal weight or remove correlations between overlapping sources.

How sensitive is this score?

The audit removes one source at a time and refits against the same overall reference panel. These published results use the matching dataset audited 2026-10-20.

Both ranks use the same surviving configurations for each removal. The cohort starts with 444 configurations supported in the original audit, including separate effort settings. These are diagnostic positions, not the default leaderboard ranks. Eligibility is not rechecked after removal.

What changes when a source is removed?
Removed source	Rank before → after	Rank movement	Cohort remaining / lost support	Score after (change)
Artificial Analysis	Comparison support lost; no rank		203 remaining / 241 lost	Unavailable
ARC Prize	198 → 192	Up 6	444 remaining / 0 lost	13.1 (+2.7 points)
Datacurve	198 → 198	No movement	444 remaining / 0 lost	8.3 (-2.1 points)
LiveCodeBench	198 → 197	Up 1	444 remaining / 0 lost	10.3 (-0.1 points)
Scale	198 → 198	No movement	444 remaining / 0 lost	11.9 (+1.5 points)
Terminal-Bench	198 → 198	No movement	444 remaining / 0 lost	10.3 (-0.1 points)
Cognition	198 → 197	Up 1	444 remaining / 0 lost	10.0 (-0.4 points)
LiveBench	197 → 193	Up 4	443 remaining / 1 lost	10.8 (+0.3 points)
SWE-rebench	198 → 195	Up 3	444 remaining / 0 lost	10.7 (+0.3 points)
Epoch AI	193 → 189	Up 4	431 remaining / 13 lost	10.7 (+0.3 points)
Vals AI	198 → 198	No movement	443 remaining / 1 lost	10.0 (-0.4 points)
Provider reports · Anthropic	198 → 198	No movement	444 remaining / 0 lost	10.4 (-0.0 points)
Provider reports · Moonshot AI	198 → 198	No movement	444 remaining / 0 lost	10.1 (-0.3 points)
Provider reports · Meta	198 → 198	No movement	444 remaining / 0 lost	10.4 (-0.0 points)
Provider reports · Mistral	198 → 198	No movement	444 remaining / 0 lost	10.4 (+0.0 points)
Provider reports · OpenAI	198 → 198	No movement	444 remaining / 0 lost	10.5 (+0.1 points)
All provider reports	198 → 198	No movement	444 remaining / 0 lost	10.2 (-0.2 points)

Lost support means a configuration no longer has a comparison path to the complete reference panel. Its rank is unavailable. A surviving path alone does not establish leaderboard eligibility.

Overlapping sources may remain correlated even with source balancing. Leave-one-source-out movement is a sensitivity diagnostic, not a spread of source-specific ranks or a confidence measure. Scoring methodology · Dated configuration audit

Every benchmark family

Removed evidence	Recomputed score	Change
arc-agi	12.7	+2.2
deepswe	8.3	-2.1
ifbench	9.1	-1.3
automationbench	11.2	+0.8
aa-lcr	9.6	-0.8
gdp-pdf	11.1	+0.7
analyst-agent	11.1	+0.7
mmmu-pro	11.1	+0.7
gpqa	9.8	-0.7
enterprise-ops	10.9	+0.5
omniscience	10.9	+0.5
epoch-game-puzzles	9.9	-0.5
simpleqa	10.9	+0.5
hle	10.9	+0.5
frontiercode	10.0	-0.4
mmlu-pro	10.7	+0.3
swe-rebench	10.7	+0.3
briefcase	10.1	-0.3
gdpval	10.2	-0.2
critpt	10.2	-0.2
livebench-instructions	10.6	+0.2
multi-swe-bench	10.2	-0.2
livebench-language	10.6	+0.2
apex-agents	10.6	+0.1
terminal-bench	10.3	-0.1
harvey	10.3	-0.1
arc-agi-3	10.3	-0.1
terminal-bench-science	10.5	+0.1
enigma-eval	10.3	-0.1
itbench	10.3	-0.1
swe-atlas-qna	10.3	-0.1
livebench-coding	10.3	-0.1
tau-bench	10.5	+0.1
livebench-reasoning	10.3	-0.1
vibe-code	10.3	-0.1
aime	10.4	-0.1
swe-atlas-test-writing	10.4	-0.0
math500	10.4	+0.0
gmmlu	10.4	+0.0
vals-code-migration	10.4	-0.0
vals-legal-research	10.4	-0.0
vals-finance-agent	10.4	-0.0
livecodebench	10.4	-0.0
vals-tax-agent	10.4	-0.0
vals-excel-modeling	10.4	-0.0
livebench-math	10.4	+0.0
frontiermath	10.4	+0.0
swe-atlas-refactoring	10.4	-0.0
livebench-data	10.4	-0.0
swe-bench-pro	10.4	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 80 observations, 18 contributing, 0 matched without graph weight and 62 excluded. Counts do not establish rank eligibility.

2 · Benchmark family or source protocol has not been reviewed
2 · Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode
2 · The evaluator reports no named effort control. This does not identify a non-reasoning configuration.
6 · Effort is not identified
23 · Supporting evidence outside the reviewed capability core
13 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
6 · No matched, identified effort unit; duplicates and unnamed comparators do not add evidence
1 · Narrow specialist biological, medical or security evaluation; preserved as raw evidence outside general capability scoring.
1 · Composite index or publisher-specific internal evaluation lacks a stable general-capability comparison unit. Composite index excluded to avoid double counting its ingredients.
6 · Legacy self-report lacks a reviewed comparison configuration

Inspect every observation and exclusion →

Benchmark results

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 2026-10-18.	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 v1.1 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 2026-10-18.	876.28 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 2026-10-18.	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 2026-10-18.	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. CritPt is under review by its authors following external feedback · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	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 2026-10-18.	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-pass RateArtificial 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 2026-10-18.	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 v2.1 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 DeepSeek V4.1 Flash (max) at 1600 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-10-18.	1,013.25 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 2026-10-18.	86.67% 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 2026-10-18.	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 2026-10-18.	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 2026-10-18.	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 2026-10-18.	-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 2026-10-18.	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 Benchmark curated by scientists across 16 disciplines. SciCode is under review following an independent audit of the dataset · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	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 2026-10-18.	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 2026-10-18.	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 2026-10-18.	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 2026-10-18.	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 2026-10-18.	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 2026-10-18.	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 2026-10-18.	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 · 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 2026-10-18.	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 2026-10-18.	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 2026-10-18.	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 · 8,915 results across 259 models · Collected 2026-10-18

NVIDIA Nemotron 3 Ultra · Reasoning

Compare with

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context

Capability score evidence

Benchmark results