Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs Nemotron 3 Ultra

Claude Haiku 4.5 leads Nemotron 3 Ultra on coding, 35.6 to 30.0 on the Vibe Coding Index, and Nemotron 3 Ultra costs 2.1x less per output token ($2.40 vs $5.00 per million). Updated October 22, 2026; 60 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace Nemotron 3 Ultra
Claude Haiku 4.5Anthropic
Coding
35.6
Overall
41.0
Output $/M
$5.00
4
Nemotron 3 UltraNVIDIA
Coding
30.0
Overall
53.1
Output $/M
$2.40
55
vs boards won of 60 shared, 1 tied

Claude Haiku 4.5 or Nemotron 3 Ultra: which to pick

Pick Claude Haiku 4.5 for coding: it scores 35.6 on the Vibe Coding Index against 30.0 for Nemotron 3 Ultra.

Pick Nemotron 3 Ultra for output tokens 2.1x cheaper ($2.40 vs $5.00 per million) and a larger context window (262K against 200K tokens).

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved taskModel BNemotron 3 UltraNVIDIA30.0/1003 independent benchmarksNo cost per solved task
Shared results
60
Claude Haiku 4.5 only
38
Nemotron 3 Ultra only
11
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Claude Haiku 4.5 35.6 from 4 benchmarks, Nemotron 3 Ultra 30.0 from 3 benchmarks.
Widest category
Math, 11.7 points apart on average over 3 shared benchmarks.
Widest single gap
LiveCodeBench (Vals AI): Claude Haiku 4.5 41.2% against Nemotron 3 Ultra 86.0%, 44.8 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against Nemotron 3 Ultra $2.40 per million output tokens, 2.1x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, Nemotron 3 Ultra 262K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryClaude Haiku 4.5BarsNemotron 3 UltraTies
Coding361 tie
Intelligence02
Agentic work05
Reasoning05
Math03
Knowledge09
Web design17
General018
All shared boards4551 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index36
Coding benchmarks for Claude Haiku 4.5 and Nemotron 3 Ultra
BenchmarkClaude Haiku 4.5Nemotron 3 UltraLeader
SWE-bench Verified66.6%Not measuredOnly Claude Haiku 4.5 measured
SWE-bench Multilingual64.7%Not measuredOnly Claude Haiku 4.5 measured
LiveBench coding48.1%Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev1330Not measuredOnly Claude Haiku 4.5 measured
AA Coding Index43.949.3Nemotron 3 Ultra
LiveCodeBench (Vals AI)41.2%86.0%Nemotron 3 Ultra
SWE-bench Verified (Vals AI)66.6%69.0%Nemotron 3 Ultra
Vibe Code Bench (Vals AI)11.4%7.6%Claude Haiku 4.5
Code migration (Vals AI)7.5%4.9%Claude Haiku 4.5
ProgramBench (Vals AI)0.0%0.0%Tie
Terminal-Bench 2.1 (Vals AI)43.8%50.9%Nemotron 3 Ultra
SciCodeNot measured40.3%Only Nemotron 3 Ultra measured
Terminal-Bench Hard (Artificial Analysis run)Not measured36.4%Only Nemotron 3 Ultra measured
Terminal-Bench35.5%Not measuredOnly Claude Haiku 4.5 measured
FrontierCodeNot measured13.6%Only Nemotron 3 Ultra measured
WeirdML45.4%43.5%Claude Haiku 4.5
LMArena Text: coding14541468Nemotron 3 Ultra
LMArena Text: software and IT14391468Nemotron 3 Ultra
LMArena WebDev: React1326Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev: HTML1318Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Haiku 4.5 and Nemotron 3 Ultra
BenchmarkClaude Haiku 4.5Nemotron 3 UltraLeader
AA Intelligence Index16.922.9Nemotron 3 Ultra
Epoch Capabilities Index142.2146.0Nemotron 3 Ultra
Agentic workLike-for-likePublic boards, shown as published, kept out of the index05
Agentic work benchmarks for Claude Haiku 4.5 and Nemotron 3 Ultra
BenchmarkClaude Haiku 4.5Nemotron 3 UltraLeader
AA Agentic Index8.020.1Nemotron 3 Ultra
LiveBench research42.2%Not measuredOnly Claude Haiku 4.5 measured
LiveBench browser40.0%Not measuredOnly Claude Haiku 4.5 measured
LiveBench long agentic11.1%Not measuredOnly Claude Haiku 4.5 measured
Finance Agent (Vals AI)31.0%37.7%Nemotron 3 Ultra
Tax Agent Bench (Vals AI)5.9%Not measuredOnly Claude Haiku 4.5 measured
Legal Research Bench (Vals AI)10.6%15.4%Nemotron 3 Ultra
Excel Modeling Benchmark (Vals AI)22.7%31.7%Nemotron 3 Ultra
τ²-Bench TelecomNot measured83.3%Only Nemotron 3 Ultra measured
APEX-AgentsNot measured22.7%Only Nemotron 3 Ultra measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%Not measuredOnly Claude Haiku 4.5 measured
Vending-Bench 2$459Not measuredOnly Claude Haiku 4.5 measured
Berkeley Function Calling Leaderboard (BFCL)68.7%Not measuredOnly Claude Haiku 4.5 measured
MCP Atlas40.2%63.1%Nemotron 3 Ultra
Neither model has a result on the other 27 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Claude Haiku 4.5 and Nemotron 3 Ultra
BenchmarkClaude Haiku 4.5Nemotron 3 UltraLeader
GPQA Diamond72.2%86.1%Nemotron 3 Ultra
LiveBench reasoning61.7%Not measuredOnly Claude Haiku 4.5 measured
MMMU Pro (Vals AI)46.1%Not measuredOnly Claude Haiku 4.5 measured
GPQA Diamond (Artificial Analysis run)Not measured86.7%Only Nemotron 3 Ultra measured
Humanity's Last Exam (Artificial Analysis run)Not measured28.4%Only Nemotron 3 Ultra measured
GPQA Diamond (Epoch AI run)71.2%85.4%Nemotron 3 Ultra
ARC-AGI47.7%Not measuredOnly Claude Haiku 4.5 measured
ARC-AGI-24.0%Not measuredOnly Claude Haiku 4.5 measured
Chess puzzles8.0%Not measuredOnly Claude Haiku 4.5 measured
Mystery game puzzlesNot measured20.0%Only Nemotron 3 Ultra measured
LMArena Text: hard prompts14211452Nemotron 3 Ultra
LMArena Text: expert14431472Nemotron 3 Ultra
LMArena Text: hard prompts in English14351453Nemotron 3 Ultra
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Claude Haiku 4.5 and Nemotron 3 Ultra
BenchmarkClaude Haiku 4.5Nemotron 3 UltraLeader
AIME82.7%Not measuredOnly Claude Haiku 4.5 measured
MGSM (Vals AI)92.2%Not measuredOnly Claude Haiku 4.5 measured
OTIS Mock AIME66.7%86.7%Nemotron 3 Ultra
ProofBenchNot measured2.0%Only Nemotron 3 Ultra measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981457Nemotron 3 Ultra
LMArena Text: mathematical work14301461Nemotron 3 Ultra
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index09
Knowledge benchmarks for Claude Haiku 4.5 and Nemotron 3 Ultra
BenchmarkClaude Haiku 4.5Nemotron 3 UltraLeader
MMLU Pro78.7%85.8%Nemotron 3 Ultra
LegalBench (Vals AI)81.2%82.1%Nemotron 3 Ultra
CaseLaw (Vals AI)56.5%Not measuredOnly Claude Haiku 4.5 measured
CorpFin (Vals AI)60.6%65.5%Nemotron 3 Ultra
TaxEval (Vals AI)67.5%73.1%Nemotron 3 Ultra
MortgageTax (Vals AI)62.2%Not measuredOnly Claude Haiku 4.5 measured
MedQA (Vals AI)79.6%Not measuredOnly Claude Haiku 4.5 measured
MedCode (Vals AI)32.7%38.6%Nemotron 3 Ultra
SimpleQA Verified13.2%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: science14061465Nemotron 3 Ultra
LMArena Text: medicine and healthcare13941456Nemotron 3 Ultra
LMArena Text: legal and government14001452Nemotron 3 Ultra
LMArena Text: business and finance14001434Nemotron 3 Ultra
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index17
Web design benchmarks for Claude Haiku 4.5 and Nemotron 3 Ultra
BenchmarkClaude Haiku 4.5Nemotron 3 UltraLeader
Design Arena: websites11221145Nemotron 3 Ultra
Design Arena: UI components10971135Nemotron 3 Ultra
Design Arena: game dev10961138Nemotron 3 Ultra
Design Arena: data viz11241141Nemotron 3 Ultra
Design Arena: 3D10711131Nemotron 3 Ultra
Design Arena: all code categories11141146Nemotron 3 Ultra
Design Arena: SVG10251069Nemotron 3 Ultra
Design Arena: ASCII art11401100Claude Haiku 4.5
LiveBench design59.9%Not measuredOnly Claude Haiku 4.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index018
General benchmarks for Claude Haiku 4.5 and Nemotron 3 Ultra
BenchmarkClaude Haiku 4.5Nemotron 3 UltraLeader
LiveBench data analysis59.3%Not measuredOnly Claude Haiku 4.5 measured
Public Benefits Bench (Vals AI)54.3%Not measuredOnly Claude Haiku 4.5 measured
SAGE (Vals AI)31.8%Not measuredOnly Claude Haiku 4.5 measured
MedScribe (Vals AI)85.2%Not measuredOnly Claude Haiku 4.5 measured
Vals Multimodal Index42.9%Not measuredOnly Claude Haiku 4.5 measured
IFBenchNot measured81.4%Only Nemotron 3 Ultra measured
Long context reasoning (AA-LCR)Not measured79.3%Only Nemotron 3 Ultra measured
DTBench73.6%90.1%Nemotron 3 Ultra
LMCA30.9%36.9%Nemotron 3 Ultra
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971445Nemotron 3 Ultra
LMArena Text: instruction following14141418Nemotron 3 Ultra
LMArena Text: creative writing13711399Nemotron 3 Ultra
LMArena Text: English14141455Nemotron 3 Ultra
LMArena Text: non-English13771427Nemotron 3 Ultra
LMArena Text: Chinese14181497Nemotron 3 Ultra
LMArena Text: German13741472Nemotron 3 Ultra
LMArena Text: Japanese1338Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: Korean13461384Nemotron 3 Ultra
LMArena Text: French14111472Nemotron 3 Ultra
LMArena Text: Spanish14211455Nemotron 3 Ultra
LMArena Text: Russian13811417Nemotron 3 Ultra
LMArena Text: Polish13431385Nemotron 3 Ultra
LMArena Text: multi-turn14091411Nemotron 3 Ultra
LMArena Text: longer queries14271437Nemotron 3 Ultra
LMArena Text: writing and language13861406Nemotron 3 Ultra
LMArena Text: entertainment and media13691397Nemotron 3 Ultra
LMArena Document1420Not measuredOnly Claude Haiku 4.5 measured
MultiChallenge50.5%Not measuredOnly Claude Haiku 4.5 measured
EQ-Bench 41064Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 18 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Haiku 4.5 and Nemotron 3 Ultra
BenchmarkClaude Haiku 4.5Nemotron 3 UltraLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Claude Haiku 4.5$0.0035Fits in one request
Nemotron 3 Ultra$0.0018Fits in one request

Nemotron 3 Ultra costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
Nemotron 3 Ultra$0.037Fits in one request

Nemotron 3 Ultra costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
Nemotron 3 Ultra$0.144Fits in one request

Nemotron 3 Ultra costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Claude Haiku 4.5 and Nemotron 3 Ultra
SpecificationAnthropic Claude Haiku 4.5NVIDIA Nemotron 3 Ultra
MakerAnthropicNVIDIA
WeightsNo public weights listedOpen weights
ReleasedOctober 15, 2025June 4, 2026
Context window200K262K
Input $/Mtok$1.00$0.60
Output $/Mtok$5.00$2.40
Coding index35.630.0
Independent measurements behind it43
Cost per solved task$0.56Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than Nemotron 3 Ultra for coding?

Pick Claude Haiku 4.5 for coding: it scores 35.6 on the Vibe Coding Index against 30.0 for Nemotron 3 Ultra. Pick Nemotron 3 Ultra for output tokens 2.1x cheaper ($2.40 vs $5.00 per million) and a larger context window (262K against 200K tokens).

Which is cheaper, Claude Haiku 4.5 or Nemotron 3 Ultra?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Nemotron 3 Ultra costs $0.60 and $2.40. Cost per solved task is known for Claude Haiku 4.5 only.

Which has the bigger context window, Claude Haiku 4.5 or Nemotron 3 Ultra?

Nemotron 3 Ultra, with 262K tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs Nemotron 3 Ultra comparison based on?

60 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 4.5's coding index rests on 4 independent benchmarks and Nemotron 3 Ultra's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/claude-haiku-4-5-vs-nvidia-nemotron-3-ultra-550b-a55b" title="Claude Haiku 4.5 vs Nemotron 3 Ultra, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/claude-haiku-4-5-vs-nvidia-nemotron-3-ultra-550b-a55b">LLMBenchmark.ai, Claude Haiku 4.5 vs Nemotron 3 Ultra</a></p>