nvidia/llama-3.1-nemotron-ultra-253b-v1

Explore nvidia/llama-3.1-nemotron-ultra-253b-v1: model specifications, capabilities, benchmark results, platform pricing and original sources.

nvidiaNim/nvidia/llama-3.1-nemotron-ultra-253b-v1

Specifications & capabilities

Published model ID
Llama-3_1-Nemotron-Ultra-253B-v1

Evaluations

1–20 / 44

BFCL

100%

source id
bfcl
leaderboard name
BFCL Irrelevance Detection
dimension
toolUse
metric
Irrelevance detection
rank
1
Original result ↗

BFCL

0%

source id
bfcl
leaderboard name
BFCL Web Search
dimension
agentic
metric
Web-search accuracy
rank
105
Original result ↗

BFCL

0%

source id
bfcl
leaderboard name
BFCL Multi Turn
dimension
agentic
metric
Multi-turn accuracy
rank
107
Original result ↗

BFCL

0%

source id
bfcl
leaderboard name
BFCL Non-Live AST
dimension
toolUse
metric
Non-live AST accuracy
rank
108
Original result ↗

BFCL

0%

source id
bfcl
leaderboard name
BFCL Relevance Detection
dimension
toolUse
metric
Relevance detection
rank
108
Original result ↗

LMArena

1,380.794

source id
lmarena
leaderboard name
LMArena Text Style Control Math
dimension
style
metric
Arena rating
rank
190
sample size
209
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.1 Nemotron Ultra 253B v1
confidence lower
1343.5848387469077
confidence upper
1418.002953546153
Original result ↗

LMArena

1,397.45

source id
lmarena
leaderboard name
LMArena Text Style Control Hard Prompts English
dimension
style
metric
Arena rating
rank
206
sample size
448
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.1 Nemotron Ultra 253B v1
confidence lower
1370.9175227195649
confidence upper
1423.9822899597098
Original result ↗

LMArena

1,359.576

source id
lmarena
leaderboard name
LMArena Text Math
dimension
general
metric
Arena rating
rank
207
sample size
209
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.1 Nemotron Ultra 253B v1
confidence lower
1322.5666575390858
confidence upper
1396.5846042287287
Original result ↗

LMArena

1,331.552

source id
lmarena
leaderboard name
LMArena Text Style Control Creative Writing
dimension
style
metric
Arena rating
rank
208
sample size
444
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.1 Nemotron Ultra 253B v1
confidence lower
1304.6482871507071
confidence upper
1358.4560107077748
Original result ↗

LMArena

1,351.467

source id
lmarena
leaderboard name
LMArena Text Style Control Instruction Following
dimension
style
metric
Arena rating
rank
209
sample size
660
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.1 Nemotron Ultra 253B v1
confidence lower
1329.8349389397756
confidence upper
1373.0982264076765
Original result ↗

LMArena

1,374.962

source id
lmarena
leaderboard name
LMArena Text Style Control Hard Prompts
dimension
style
metric
Arena rating
rank
213
sample size
713
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.1 Nemotron Ultra 253B v1
confidence lower
1353.8295692132156
confidence upper
1396.0944148676558
Original result ↗

LMArena

1,375.921

source id
lmarena
leaderboard name
LMArena Text Style Control English
dimension
style
metric
Arena rating
rank
215
sample size
1491
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.1 Nemotron Ultra 253B v1
confidence lower
1361.0366075090328
confidence upper
1390.8052522175742
Original result ↗

LMArena

1,314.215

source id
lmarena
leaderboard name
LMArena Text Creative Writing
dimension
general
metric
Arena rating
rank
215
sample size
444
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.1 Nemotron Ultra 253B v1
confidence lower
1287.8250494675092
confidence upper
1340.6040602341113
Original result ↗

LMArena

1,386.706

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Software And It Services
dimension
style
metric
Arena rating
rank
221
sample size
588
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.1 Nemotron Ultra 253B v1
confidence lower
1363.207344935393
confidence upper
1410.2038973909057
Original result ↗

LMArena

1,390.596

source id
lmarena
leaderboard name
LMArena Text Style Control Coding
dimension
style
metric
Arena rating
rank
226
sample size
367
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.1 Nemotron Ultra 253B v1
confidence lower
1360.9468852078107
confidence upper
1420.2441556774218
Original result ↗

LMArena

1,341.755

source id
lmarena
leaderboard name
LMArena Text Style Control Multi Turn
dimension
style
metric
Arena rating
rank
226
sample size
374
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.1 Nemotron Ultra 253B v1
confidence lower
1311.6184914260946
confidence upper
1371.8917942935932
Original result ↗

LMArena

1,347.589

source id
lmarena
leaderboard name
LMArena Text Style Control Overall
dimension
style
metric
Arena rating
rank
227
sample size
2549
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.1 Nemotron Ultra 253B v1
confidence lower
1335.9132869298517
confidence upper
1359.265262222361
Original result ↗

Provider specifications & access

1–1 / 1

nvidia/llama-3.1-nemotron-ultra-253b-v1 ↗

source model id
nvidia/llama-3.1-nemotron-ultra-253b-v1
hosting
nvidia-inference-listed
platforms
  • NVIDIA inference catalog
architecture
input_modalities
    output_modalities
      capabilities
        availability
        Listed by inference API; runtime availability unverified

        Safety assessments

        1–1 / 1

        Foundation Model Transparency Index 2025 ↗

        31 / 100

        source id
        stanfordFMTI
        canonical model id
        nvidiaNim/nvidia/llama-3.1-nemotron-ultra-253b-v1
        taxonomy
        transparency
        hazard category
        transparency
        hazard name
        Organization transparency
        policy area
        Meta
        assessment type
        organization-level disclosure
        metric
        disclosure_score
        result label
        31 / 100
        sample size
        100
        updated at
        2026-11-09T18:08:05.227Z

        Original sources

        1–5 / 5

        Hugging Face · Model reference ↗

        NVIDIA · Catalog ↗

        GitHub · Catalog ↗

        LMArena · Catalog ↗

        gorilla.cs.berkeley.edu · Catalog ↗

        Source links

        1–4 / 4

        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