RankingNVIDIA Nemotron 3 Ultra

NVIDIA Nemotron 3 Ultra

Data updated 22 Oct 2026

47 published benchmark measures · 13 benchmark families contribute across 6 task areas. 3 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →

Model evidence summary

This profile combines published settings. It is not a runnable configuration or a leaderboard rank. Compare measured configurations →

Performance profile

Capabilities

Adjusted comparison score · 0–100

Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.

Agentic2 families · 1 with independent evidence · Supported2.7

2 core families; 45 direct opponents across 16 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 2.3–3.6; 2/13 scenarios unsupported. Without one publisher: 1.8–71.0; 1/15 unsupported. Smoothing check: 1.1–8.2; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage; source sensitivity still requires inspection. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

GDPval: 43.5 observed win share
NVIDIA, artificialanalysis.ai · Source 1 Source 2
Browsecomp: 25.0 observed win share
NVIDIA · Source 1

Hard reasoning3 families · 0 with independent evidence · Supported13.3

3 core families; 5 direct opponents across 5 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 4.0–25.4; 0/6 scenarios unsupported. Without one publisher: 3.2–53.8; 1/16 unsupported. Smoothing check: 5.5–25.8; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

GPQA: 25.0 observed win share
NVIDIA, artificialanalysis.ai · Source 1 Source 2
Humanity’s Last Exam: 12.5 observed win share
NVIDIA · Source 1 Source 2
Imo Answerbench: 75.0 observed win share
NVIDIA · Source 1 Source 2

Coding3 families · 0 with independent evidence · Supported1.7

3 core families; 4 direct opponents across 4 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 0.4–16.4; 0/6 scenarios unsupported. Without one publisher: 1.0–7.3; 1/19 unsupported. Smoothing check: 0.8–5.5; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

LiveCodeBench: 75.0 observed win share
NVIDIA · Source 1
SWE-bench Multilingual: 0.0 observed win share
NVIDIA · Source 1
SWE-bench Verified: 0.0 observed win share
NVIDIA · Source 1

Human pref1 families · 1 with independent evidence · PreliminaryUnknown

1 core families; 41 direct opponents across 13 labs. No connected comparison to the complete reference panel

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 1/1 scenarios unsupported. Without one publisher: No supported estimate; 1/1 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: cross-family and cross-publisher predictions could not be evaluated from the available comparison network. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Human preference (Arena): 82.9 observed win share
lmarena.ai · Source 1

Knowledge1 families · 0 with independent evidence · PreliminaryUnknown

1 core families; 4 direct opponents across 4 labs. No connected comparison to the complete reference panel

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 4/4 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: almost no publisher-held-out comparisons remained estimable. Cross-source validity is unresolved. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

MMLU-Pro: 37.5 observed win share
NVIDIA · Source 1 Source 2

MultimodalNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 8/8 scenarios unsupported. Without one publisher: No supported estimate; 8/8 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: limited publisher-held-out coverage. Cross-source validity is unresolved. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Long context3 families · 0 with independent evidence · PreliminaryUnknown

3 core families; 4 direct opponents across 4 labs. No connected comparison to the complete reference panel

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 5/5 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts underperformed neutral predictions. Treat this as an exploratory estimate. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Aa Lcr: 0.0 observed win share
NVIDIA · Source 1
Longbench: 0.0 observed win share
NVIDIA · Source 1
Ruler 1M: 100.0 observed win share
NVIDIA · Source 1

Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.

Reported effort · Thinking + unspecified

Settings reported in this model's published benchmark results, including results outside the aggregate. Effort names are provider-specific. These are not API defaults or equal compute budgets.

Thinking: 12 observations
Not specified: 39 observations

Mixed settings means multiple settings occur in the evidence. Best across efforts means the source selected its best reported result across settings; it does not mean Max. Unspecified settings stay unknown. This model-summary chart combines reported settings. The leaderboard keeps identified configurations separate and excludes unknown effort.

Inspect each result and its source ↓ · Download effort evidence

Score contributions and missing evidence

13 contributing families across 6 capabilities. Fixed reference panels do not change when the catalog expands.

Capability is fitted jointly across families. Capability estimates below describe different task areas; their weighted sum is not the Capability score.

Results without reviewed compatibility or a reference match remain in the raw evidence below. Coverage counts only contributing results.

Model information & shareable badge

Lab: NVIDIA
Catalog status: open-weights-available
Availability: Open weights available for self-hosting
Family: Nemotron 3
Released: —
Context: —
License: —
Model card: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Default Capability family coverage: /badge/nemotron-3-ultra.svg

Benchmark scores & sources

Original results, evaluation harnesses, and evidence behind this model.

Benchmark	Bucket	Score	Harness	Evidence	Source-recorded date
AA-LCR · source release snapshot; version not specified	Long context	65.4% Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 65.4 The linked NVIDIA reproduction recipe explicitly enables thinking for this model and benchmark. It does not establish Low/Medium/High/Max or a fixed reasoning-token budget; the request adapter removes max_tokens and max_completion_tokens. Comparator settings are not specified by this recipe. nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: AA-LCR · reviewed 2026-09-06	Published configuration Effort: Thinking contributes to capability	lab self-report	Reviewed 2026-09-06
Apex-Shortlist (no tools) · source release snapshot; version not specified	Supporting evidence	74.9% Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 74.9 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: Apex-Shortlist (no tools) · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
Apex-Shortlist (with tools) · source release snapshot; version not specified	Supporting evidence	84.8% Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 84.8 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: Apex-Shortlist (with tools) · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
Artificial Analysis Cyber Index	Supporting evidence	13.0784136433712	Artificial Analysis Stirrup · Cyber Index v1.0 · reasoning Effort: Reasoning Cyber Index source settings Artificial Analysis Stirrup, v1.0. Display only. This composite measures defensive source-code tasks. Successful capability scores depend on safety refusals, and refusal rates are reported separately. It does not enter weighted Overall. Official Cyber Index board	official board Supporting evidence outside the reviewed capability core	2026-10-21
Artificial Analysis Intelligence Index	Supporting evidence	38	AA Intelligence Index Effort: Not specified	official board Composite index or publisher-specific internal evaluation lacks a stable general-capability comparison unit. Composite index excluded to avoid double counting its ingredients.	2026-09-02
AutomationBench-AA	Supporting evidence	2.986349541593992%	Artificial Analysis AutomationBench-AA Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-10-20
BrowseComp	Agentic	44.4%	BrowseComp reported Effort: Not specified	lab self-report Legacy self-report lacks a reviewed comparison configuration	2026-06-04
BrowseComp · source release snapshot; version not specified	Agentic	44.4% Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 44.4 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: BrowseComp · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
CritPt (no tools) · source release snapshot; version not specified	Supporting evidence	3.1% Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 3.1 The linked NVIDIA reproduction recipe explicitly enables thinking for this model and benchmark. It does not establish Low/Medium/High/Max or a fixed reasoning-token budget; the request adapter removes max_tokens and max_completion_tokens. Comparator settings are not specified by this recipe. nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: CritPt (no tools) · reviewed 2026-09-06	Published configuration Effort: Thinking	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
DAYJOB Finance	Supporting evidence	0%	DAYJOB Finance · unspecified Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-10-21
DAYJOB Healthcare	Supporting evidence	0%	DAYJOB Healthcare · unspecified Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-10-21
GDPVal · source release snapshot; version not specified	Agentic	46.7% Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 46.7 The linked NVIDIA reproduction recipe explicitly enables thinking for this model and benchmark. It does not establish Low/Medium/High/Max or a fixed reasoning-token budget; the request adapter removes max_tokens and max_completion_tokens. Comparator settings are not specified by this recipe. nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: GDPVal · reviewed 2026-09-06	Published configuration Effort: Thinking contributes to capability	lab self-report	Reviewed 2026-09-06
GDPval-AA	Agentic	1011	Artificial Analysis GDPval-AA Effort: Not specified contributes to capability	official board	2026-10-22
GPQA (no tools) · source release snapshot; version not specified	Hard reasoning	87% Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 87.0 The linked NVIDIA reproduction recipe explicitly enables thinking for this model and benchmark. It does not establish Low/Medium/High/Max or a fixed reasoning-token budget; the request adapter removes max_tokens and max_completion_tokens. Comparator settings are not specified by this recipe. nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: GPQA (no tools) · reviewed 2026-09-06	Published configuration Effort: Thinking contributes to capability	lab self-report	Reviewed 2026-09-06
GPQA Diamond	Hard reasoning	86.667%	GPQA Diamond reported Effort: Not specified contributes to capability	independent repro	2026-10-13
HLE (no tools) · source release snapshot; version not specified	Hard reasoning	26.7% Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 26.7 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: HLE (no tools) · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
HLE (with tools) · source release snapshot; version not specified	Hard reasoning	37.4% Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 37.4 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: HLE (with tools) · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Humanity's Last Exam	Hard reasoning	26.7%	HLE no tools Effort: Not specified	lab self-report Legacy self-report lacks a reviewed comparison configuration	2026-06-04
IFBench (prompt loose) · source release snapshot; version not specified	Supporting evidence	81.7% Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 81.7 The linked NVIDIA reproduction recipe explicitly enables thinking for this model and benchmark. It does not establish Low/Medium/High/Max or a fixed reasoning-token budget; the request adapter removes max_tokens and max_completion_tokens. Comparator settings are not specified by this recipe. nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: IFBench (prompt loose) · reviewed 2026-09-06	Published configuration Effort: Thinking	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
IMOAnswerBench (no tools) · source release snapshot; version not specified	Hard reasoning	88.6% Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 88.6 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: IMOAnswerBench (no tools) · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
IMOAnswerBench (with tools) · source release snapshot; version not specified	Hard reasoning	92.3% Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 92.3 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: IMOAnswerBench (with tools) · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
IOI 2025 · source release snapshot; version not specified	Supporting evidence	570 points Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 570.0 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: IOI 2025 · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
LiveCodeBench	Coding	89%	LiveCodeBench pass@1 Effort: Not specified	lab self-report Legacy self-report lacks a reviewed comparison configuration	2026-06-04
LiveCodeBench (v6) · source release snapshot; version not specified	Coding	89% Reported settings & source NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 89.0 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: LiveCodeBench (v6) · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
LMArena Agent Arena	Supporting evidence	-12.27	LMArena Agent Arena · unspecified Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-10-20