Enter opens the highlighted result. Esc closes.

MiniMax M2.7 vs Nemotron 3 Ultra

MiniMax M2.7 leads Nemotron 3 Ultra on coding, 36.2 to 30.0 on the Vibe Coding Index, and MiniMax M2.7 costs 2.0x less per output token ($1.20 vs $2.40 per million). Updated October 23, 2026; 63 benchmarks have a result for both.

Replace MiniMax M2.7 Replace Nemotron 3 Ultra
MiniMax M2.7MiniMax
Coding
36.2
Overall
44.5
Output $/M
$1.20
22
Nemotron 3 UltraNVIDIA
Coding
30.0
Overall
53.1
Output $/M
$2.40
40
vs boards won of 63 shared, 1 tied

MiniMax M2.7 or Nemotron 3 Ultra: which to pick

Pick MiniMax M2.7 for coding: it scores 36.2 on the Vibe Coding Index against 30.0 for Nemotron 3 Ultra.

Pick Nemotron 3 Ultra for a larger context window (262K against 205K tokens) and work measured by LiveCodeBench (Vals AI) or Terminal-Bench 2.1 (Vals AI), where it leads.

Model AMiniMax M2.7MiniMax36.2/1003 independent benchmarks$0.64 per solved taskModel BNemotron 3 UltraNVIDIA30.0/1003 independent benchmarksNo cost per solved task
Shared results
63
MiniMax M2.7 only
11
Nemotron 3 Ultra only
8
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
MiniMax M2.7 36.2 from 3 benchmarks, Nemotron 3 Ultra 30.0 from 3 benchmarks.
Widest category
Web design, 9.1 points apart on average over 8 shared benchmarks.
Widest single gap
LMArena Text: German: MiniMax M2.7 1398 against Nemotron 3 Ultra 1474, 12.7 points apart on a 0 to 100 scale.
Output price
MiniMax M2.7 $1.20 against Nemotron 3 Ultra $2.40 per million output tokens, 2.0x apart.
Context window
MiniMax M2.7 takes 205K 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
CategoryMiniMax M2.7BarsNemotron 3 UltraTies
Coding651 tie
Intelligence02
Agentic work14
Reasoning33
Math12
Knowledge18
Web design80
General216
All shared boards22401 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index65
Coding benchmarks for MiniMax M2.7 and Nemotron 3 Ultra
BenchmarkMiniMax M2.7Nemotron 3 UltraLeader
LMArena WebDev1398Not measuredOnly MiniMax M2.7 measured
AA Coding Index52.649.3MiniMax M2.7
LiveCodeBench (Vals AI)79.9%86.0%Nemotron 3 Ultra
SWE-bench Verified (Vals AI)73.8%69.0%MiniMax M2.7
Vibe Code Bench (Vals AI)11.9%7.6%MiniMax M2.7
Code migration (Vals AI)8.7%4.9%MiniMax M2.7
ProgramBench (Vals AI)0.0%0.0%Tie
Terminal-Bench 2.1 (Vals AI)48.7%50.9%Nemotron 3 Ultra
SciCode50.1%40.3%MiniMax M2.7
Terminal-Bench Hard (Artificial Analysis run)39.4%36.4%MiniMax M2.7
Terminal-Bench45.1%Not measuredOnly MiniMax M2.7 measured
FrontierCodeNot measured13.6%Only Nemotron 3 Ultra measured
WeirdML37.0%43.5%Nemotron 3 Ultra
ALE-Bench599.3Not measuredOnly MiniMax M2.7 measured
LMArena Text: coding14541467Nemotron 3 Ultra
LMArena Text: software and IT14451468Nemotron 3 Ultra
LMArena WebDev: React1388Not measuredOnly MiniMax M2.7 measured
LMArena WebDev: HTML1402Not measuredOnly MiniMax M2.7 measured
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for MiniMax M2.7 and Nemotron 3 Ultra
BenchmarkMiniMax M2.7Nemotron 3 UltraLeader
AA Intelligence Index22.822.9Nemotron 3 Ultra
Epoch Capabilities Index145.8146.0Nemotron 3 Ultra
Agentic workLike-for-likePublic boards, shown as published, kept out of the index14
Agentic work benchmarks for MiniMax M2.7 and Nemotron 3 Ultra
BenchmarkMiniMax M2.7Nemotron 3 UltraLeader
AA Agentic Index15.320.1Nemotron 3 Ultra
Finance Agent (Vals AI)27.9%37.7%Nemotron 3 Ultra
Tax Agent Bench (Vals AI)6.9%Not measuredOnly MiniMax M2.7 measured
Legal Research Bench (Vals AI)10.6%15.4%Nemotron 3 Ultra
Excel Modeling Benchmark (Vals AI)28.4%31.7%Nemotron 3 Ultra
τ²-Bench Telecom84.8%83.3%MiniMax M2.7
APEX-AgentsNot measured22.7%Only Nemotron 3 Ultra measured
MCP AtlasNot measured63.1%Only Nemotron 3 Ultra measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index33
Reasoning benchmarks for MiniMax M2.7 and Nemotron 3 Ultra
BenchmarkMiniMax M2.7Nemotron 3 UltraLeader
GPQA Diamond86.6%86.1%MiniMax M2.7
GPQA Diamond (Artificial Analysis run)87.4%86.7%MiniMax M2.7
Humanity's Last Exam (Artificial Analysis run)29.6%28.4%MiniMax M2.7
GPQA Diamond (Epoch AI run)Not measured85.4%Only Nemotron 3 Ultra measured
Mystery game puzzlesNot measured20.0%Only Nemotron 3 Ultra measured
LMArena Text: hard prompts14231452Nemotron 3 Ultra
LMArena Text: expert14431472Nemotron 3 Ultra
LMArena Text: hard prompts in English14411453Nemotron 3 Ultra
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index12
Math benchmarks for MiniMax M2.7 and Nemotron 3 Ultra
BenchmarkMiniMax M2.7Nemotron 3 UltraLeader
AIME91.0%Not measuredOnly MiniMax M2.7 measured
OTIS Mock AIMENot measured86.7%Only Nemotron 3 Ultra measured
ProofBench3.0%2.0%MiniMax M2.7
LMArena Text: math14211457Nemotron 3 Ultra
LMArena Text: mathematical work14371462Nemotron 3 Ultra
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index18
Knowledge benchmarks for MiniMax M2.7 and Nemotron 3 Ultra
BenchmarkMiniMax M2.7Nemotron 3 UltraLeader
MMLU Pro80.4%85.8%Nemotron 3 Ultra
LegalBench (Vals AI)84.0%82.1%MiniMax M2.7
CaseLaw (Vals AI)60.9%Not measuredOnly MiniMax M2.7 measured
CorpFin (Vals AI)61.2%65.5%Nemotron 3 Ultra
TaxEval (Vals AI)66.6%73.1%Nemotron 3 Ultra
MedCode (Vals AI)34.4%38.6%Nemotron 3 Ultra
LMArena Text: science14161465Nemotron 3 Ultra
LMArena Text: medicine and healthcare14091455Nemotron 3 Ultra
LMArena Text: legal and government14031453Nemotron 3 Ultra
LMArena Text: business and finance14071435Nemotron 3 Ultra
Neither model has a result on the other 10 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for MiniMax M2.7 and Nemotron 3 Ultra
BenchmarkMiniMax M2.7Nemotron 3 UltraLeader
Design Arena: websites12421145MiniMax M2.7
Design Arena: UI components12081135MiniMax M2.7
Design Arena: game dev12091138MiniMax M2.7
Design Arena: data viz12331142MiniMax M2.7
Design Arena: 3D11941132MiniMax M2.7
Design Arena: all code categories12331146MiniMax M2.7
Design Arena: SVG11361069MiniMax M2.7
Design Arena: ASCII art11361100MiniMax M2.7
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index216
General benchmarks for MiniMax M2.7 and Nemotron 3 Ultra
BenchmarkMiniMax M2.7Nemotron 3 UltraLeader
MedScribe (Vals AI)79.9%Not measuredOnly MiniMax M2.7 measured
IFBench75.7%81.4%Nemotron 3 Ultra
Long context reasoning (AA-LCR)78.3%79.3%Nemotron 3 Ultra
DTBenchNot measured90.1%Only Nemotron 3 Ultra measured
LMCANot measured36.9%Only Nemotron 3 Ultra measured
ExploitBench13.3%Not measuredOnly MiniMax M2.7 measured
LMArena Text14051445Nemotron 3 Ultra
LMArena Text: instruction following14051418Nemotron 3 Ultra
LMArena Text: creative writing13541398Nemotron 3 Ultra
LMArena Text: English14261454Nemotron 3 Ultra
LMArena Text: non-English13831427Nemotron 3 Ultra
LMArena Text: Chinese14411498Nemotron 3 Ultra
LMArena Text: German13981474Nemotron 3 Ultra
LMArena Text: Japanese1259Not measuredOnly MiniMax M2.7 measured
LMArena Text: Korean13161385Nemotron 3 Ultra
LMArena Text: French14241473Nemotron 3 Ultra
LMArena Text: Spanish14031454Nemotron 3 Ultra
LMArena Text: Russian13841417Nemotron 3 Ultra
LMArena Text: Polish13881385MiniMax M2.7
LMArena Text: multi-turn14121411MiniMax M2.7
LMArena Text: longer queries14191437Nemotron 3 Ultra
LMArena Text: writing and language13761405Nemotron 3 Ultra
LMArena Text: entertainment and media13611397Nemotron 3 Ultra
Neither model has a result on the other 25 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for MiniMax M2.7 and Nemotron 3 Ultra
BenchmarkMiniMax M2.7Nemotron 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

MiniMax M2.7$0.0009Fits in one request
Nemotron 3 Ultra$0.0018Fits in one request

MiniMax M2.7 costs less

Repository review

50K input + 3K output tokens

MiniMax M2.7$0.019Fits in one request
Nemotron 3 Ultra$0.037Fits in one request

MiniMax M2.7 costs less

Agent loop

200K input + 10K output tokens

MiniMax M2.7$0.072Exceeds the context window
Nemotron 3 Ultra$0.144Fits in one request

MiniMax M2.7 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 MiniMax M2.7 and Nemotron 3 Ultra
SpecificationMiniMax M2.7NVIDIA Nemotron 3 Ultra
MakerMiniMaxNVIDIA
WeightsOpen weightsOpen weights
ReleasedMarch 18, 2026June 4, 2026
Context window205K262K
Input $/Mtok$0.30$0.60
Output $/Mtok$1.20$2.40
Coding index36.230.0
Independent measurements behind it33
Cost per solved task$0.64Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M2.7 better than Nemotron 3 Ultra for coding?

Pick MiniMax M2.7 for coding: it scores 36.2 on the Vibe Coding Index against 30.0 for Nemotron 3 Ultra. Pick Nemotron 3 Ultra for a larger context window (262K against 205K tokens) and work measured by LiveCodeBench (Vals AI) or Terminal-Bench 2.1 (Vals AI), where it leads.

Which is cheaper, MiniMax M2.7 or Nemotron 3 Ultra?

MiniMax M2.7 costs $0.30 per million input tokens and $1.20 per million output tokens; Nemotron 3 Ultra costs $0.60 and $2.40. Cost per solved task is known for MiniMax M2.7 only.

Which has the bigger context window, MiniMax M2.7 or Nemotron 3 Ultra?

Nemotron 3 Ultra, with 262K tokens against 205K.

How many benchmarks is the MiniMax M2.7 vs Nemotron 3 Ultra comparison based on?

63 benchmarks have a result for both models as of October 23, 2026. MiniMax M2.7's coding index rests on 3 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/minimax-minimax-m2-7-vs-nvidia-nemotron-3-ultra-550b-a55b" title="MiniMax M2.7 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/minimax-minimax-m2-7-vs-nvidia-nemotron-3-ultra-550b-a55b">LLMBenchmark.ai, MiniMax M2.7 vs Nemotron 3 Ultra</a></p>