Enter opens the highlighted result. Esc closes.

Codestral 2508 vs Nemotron 3 Ultra

Codestral 2508 costs 2.7x less per output token than Nemotron 3 Ultra ($0.90 vs $2.40 per million). Updated October 22, 2026; 6 benchmarks have a result for both.

Codestral 2508Mistral AI
Coding
No data
Overall
No data
Output $/M
$0.90
0
Nemotron 3 UltraNVIDIA
Coding
30.0
Overall
53.1
Output $/M
$2.40
6
vs boards won of 6 shared

Codestral 2508 or Nemotron 3 Ultra: which to pick

Only Nemotron 3 Ultra has a coding score, 30.0 on the Vibe Coding Index; Codestral 2508 has none, so the two cannot be ranked on coding.

Pick Codestral 2508 for output tokens 2.7x cheaper ($0.90 vs $2.40 per million).

Shared results
6
Codestral 2508 only
2
Nemotron 3 Ultra only
64
Like-for-like categories
1 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
Codestral 2508 not benchmarked, Nemotron 3 Ultra 30.0 from 3 benchmarks.
Widest category
Web design, 16.7 points apart on average over 6 shared benchmarks.
Widest single gap
Design Arena: game dev: Codestral 2508 967 against Nemotron 3 Ultra 1138, 21.4 points apart on a 0 to 100 scale.
Output price
Codestral 2508 $0.90 against Nemotron 3 Ultra $2.40 per million output tokens, 2.7x apart.
Context window
Codestral 2508 takes 256K 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
CategoryCodestral 2508BarsNemotron 3 UltraTies
Web design06
All shared boards06
CodingDirectional onlySix of these boards feed the Vibe Coding Index14 boards, none shared
Coding benchmarks for Codestral 2508 and Nemotron 3 Ultra
BenchmarkCodestral 2508Nemotron 3 UltraLeader
AA Coding IndexNot measured49.3Only Nemotron 3 Ultra measured
LiveCodeBench (Vals AI)Not measured86.0%Only Nemotron 3 Ultra measured
SWE-bench Verified (Vals AI)Not measured69.0%Only Nemotron 3 Ultra measured
Vibe Code Bench (Vals AI)Not measured7.6%Only Nemotron 3 Ultra measured
Code migration (Vals AI)Not measured4.9%Only Nemotron 3 Ultra measured
ProgramBench (Vals AI)Not measured0.0%Only Nemotron 3 Ultra measured
Terminal-Bench 2.1 (Vals AI)Not measured50.9%Only Nemotron 3 Ultra measured
SciCodeNot measured40.3%Only Nemotron 3 Ultra measured
Terminal-Bench Hard (Artificial Analysis run)Not measured36.4%Only Nemotron 3 Ultra measured
FrontierCodeNot measured13.6%Only Nemotron 3 Ultra measured
WeirdMLNot measured43.5%Only Nemotron 3 Ultra measured
ALE-Bench137.8Not measuredOnly Codestral 2508 measured
LMArena Text: codingNot measured1468Only Nemotron 3 Ultra measured
LMArena Text: software and ITNot measured1468Only Nemotron 3 Ultra measured
Neither model has a result on the other 25 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for Codestral 2508 and Nemotron 3 Ultra
BenchmarkCodestral 2508Nemotron 3 UltraLeader
AA Intelligence IndexNot measured22.9Only Nemotron 3 Ultra measured
Epoch Capabilities IndexNot measured146.0Only Nemotron 3 Ultra measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Agentic work benchmarks for Codestral 2508 and Nemotron 3 Ultra
BenchmarkCodestral 2508Nemotron 3 UltraLeader
AA Agentic IndexNot measured20.1Only Nemotron 3 Ultra measured
Finance Agent (Vals AI)Not measured37.7%Only Nemotron 3 Ultra measured
Legal Research Bench (Vals AI)Not measured15.4%Only Nemotron 3 Ultra measured
Excel Modeling Benchmark (Vals AI)Not measured31.7%Only Nemotron 3 Ultra measured
τ²-Bench TelecomNot measured83.3%Only Nemotron 3 Ultra measured
APEX-AgentsNot measured22.7%Only Nemotron 3 Ultra measured
Neither model has a result on the other 35 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Reasoning benchmarks for Codestral 2508 and Nemotron 3 Ultra
BenchmarkCodestral 2508Nemotron 3 UltraLeader
GPQA DiamondNot measured86.1%Only Nemotron 3 Ultra 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)Not measured85.4%Only Nemotron 3 Ultra measured
Mystery game puzzlesNot measured20.0%Only Nemotron 3 Ultra measured
LMArena Text: hard promptsNot measured1452Only Nemotron 3 Ultra measured
LMArena Text: expertNot measured1472Only Nemotron 3 Ultra measured
LMArena Text: hard prompts in EnglishNot measured1453Only Nemotron 3 Ultra measured
Kagi LLM Benchmark32.5%Not measuredOnly Codestral 2508 measured
Neither model has a result on the other 13 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Math benchmarks for Codestral 2508 and Nemotron 3 Ultra
BenchmarkCodestral 2508Nemotron 3 UltraLeader
OTIS Mock AIMENot measured86.7%Only Nemotron 3 Ultra measured
ProofBenchNot measured2.0%Only Nemotron 3 Ultra measured
LMArena Text: mathNot measured1457Only Nemotron 3 Ultra measured
LMArena Text: mathematical workNot measured1461Only Nemotron 3 Ultra measured
Neither model has a result on the other 9 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Knowledge benchmarks for Codestral 2508 and Nemotron 3 Ultra
BenchmarkCodestral 2508Nemotron 3 UltraLeader
MMLU ProNot measured85.8%Only Nemotron 3 Ultra measured
LegalBench (Vals AI)Not measured82.1%Only Nemotron 3 Ultra measured
CorpFin (Vals AI)Not measured65.5%Only Nemotron 3 Ultra measured
TaxEval (Vals AI)Not measured73.1%Only Nemotron 3 Ultra measured
MedCode (Vals AI)Not measured38.6%Only Nemotron 3 Ultra measured
LMArena Text: scienceNot measured1465Only Nemotron 3 Ultra measured
LMArena Text: medicine and healthcareNot measured1456Only Nemotron 3 Ultra measured
LMArena Text: legal and governmentNot measured1452Only Nemotron 3 Ultra measured
LMArena Text: business and financeNot measured1434Only Nemotron 3 Ultra measured
Neither model has a result on the other 9 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index06
Web design benchmarks for Codestral 2508 and Nemotron 3 Ultra
BenchmarkCodestral 2508Nemotron 3 UltraLeader
Design Arena: websites10121145Nemotron 3 Ultra
Design Arena: UI components10141136Nemotron 3 Ultra
Design Arena: game dev9671138Nemotron 3 Ultra
Design Arena: data viz10171142Nemotron 3 Ultra
Design Arena: 3D10191131Nemotron 3 Ultra
Design Arena: all code categories10071146Nemotron 3 Ultra
Design Arena: SVGNot measured1069Only Nemotron 3 Ultra measured
Design Arena: ASCII artNot measured1100Only Nemotron 3 Ultra measured
Neither model has a result on the other 1 board here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index20 boards, none shared
General benchmarks for Codestral 2508 and Nemotron 3 Ultra
BenchmarkCodestral 2508Nemotron 3 UltraLeader
IFBenchNot measured81.4%Only Nemotron 3 Ultra measured
Long context reasoning (AA-LCR)Not measured79.3%Only Nemotron 3 Ultra measured
DTBenchNot measured90.1%Only Nemotron 3 Ultra measured
LMCANot measured36.9%Only Nemotron 3 Ultra measured
LMArena TextNot measured1445Only Nemotron 3 Ultra measured
LMArena Text: instruction followingNot measured1418Only Nemotron 3 Ultra measured
LMArena Text: creative writingNot measured1399Only Nemotron 3 Ultra measured
LMArena Text: EnglishNot measured1455Only Nemotron 3 Ultra measured
LMArena Text: non-EnglishNot measured1427Only Nemotron 3 Ultra measured
LMArena Text: ChineseNot measured1497Only Nemotron 3 Ultra measured
LMArena Text: GermanNot measured1472Only Nemotron 3 Ultra measured
LMArena Text: KoreanNot measured1384Only Nemotron 3 Ultra measured
LMArena Text: FrenchNot measured1472Only Nemotron 3 Ultra measured
LMArena Text: SpanishNot measured1455Only Nemotron 3 Ultra measured
LMArena Text: RussianNot measured1417Only Nemotron 3 Ultra measured
LMArena Text: PolishNot measured1385Only Nemotron 3 Ultra measured
LMArena Text: multi-turnNot measured1411Only Nemotron 3 Ultra measured
LMArena Text: longer queriesNot measured1437Only Nemotron 3 Ultra measured
LMArena Text: writing and languageNot measured1406Only Nemotron 3 Ultra measured
LMArena Text: entertainment and mediaNot measured1397Only Nemotron 3 Ultra measured
Neither model has a result on the other 26 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Codestral 2508 and Nemotron 3 Ultra
BenchmarkCodestral 2508Nemotron 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

Codestral 2508$0.0008Fits in one request
Nemotron 3 Ultra$0.0018Fits in one request

Codestral 2508 costs less

Repository review

50K input + 3K output tokens

Codestral 2508$0.018Fits in one request
Nemotron 3 Ultra$0.037Fits in one request

Codestral 2508 costs less

Agent loop

200K input + 10K output tokens

Codestral 2508$0.069Fits in one request
Nemotron 3 Ultra$0.144Fits in one request

Codestral 2508 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 Codestral 2508 and Nemotron 3 Ultra
SpecificationMistral Codestral 2508NVIDIA Nemotron 3 Ultra
MakerMistral AINVIDIA
WeightsNo public weights listedOpen weights
ReleasedAugust 1, 2025June 4, 2026
Context window256K262K
Input $/Mtok$0.30$0.60
Output $/Mtok$0.90$2.40
Coding indexNot benchmarked30.0
Independent measurements behind it03
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Codestral 2508 better than Nemotron 3 Ultra for coding?

Only Nemotron 3 Ultra has a coding score, 30.0 on the Vibe Coding Index; Codestral 2508 has none, so the two cannot be ranked on coding. Pick Codestral 2508 for output tokens 2.7x cheaper ($0.90 vs $2.40 per million).

Which is cheaper, Codestral 2508 or Nemotron 3 Ultra?

Codestral 2508 costs $0.30 per million input tokens and $0.90 per million output tokens; Nemotron 3 Ultra costs $0.60 and $2.40. Cost per solved task is known for neither of them.

Which has the bigger context window, Codestral 2508 or Nemotron 3 Ultra?

Nemotron 3 Ultra, with 262K tokens against 256K.

How many benchmarks is the Codestral 2508 vs Nemotron 3 Ultra comparison based on?

6 benchmarks have a result for both models as of October 22, 2026. Codestral 2508's coding index rests on 0 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