Enter opens the highlighted result. Esc closes.

Llama 3.2 1B Instruct vs Phi 4

Updated October 21, 2026. 37 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Llama 3.2 1B Instruct Replace Phi 4
Llama 3.2 1B InstructMeta Llama
Coding
No data
Overall
4.8
Output $/M
$0.201
2
Phi 4Microsoft
Coding
No data
Overall
5.9
Output $/M
$0.14
34
vs boards won of 37 shared, 1 tied

Decision reading

Neither model has a coding score yet, so the two cannot be ranked on coding.

Llama 3.2 1B Instruct has the edge where the context window is larger, 60K against 16K tokens, and where what matters is LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model ALlama 3.2 1B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved taskModel BPhi 4MicrosoftNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
37
Llama 3.2 1B Instruct only
0
Phi 4 only
8
Like-for-like categories
7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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
Llama 3.2 1B Instruct not benchmarked, Phi 4 not benchmarked.
Widest category
Knowledge, 34.1 points apart on average over 5 shared benchmarks.
Widest single gap
MMLU Pro (Artificial Analysis run): Llama 3.2 1B Instruct 20.0% against Phi 4 71.4%, 51.4 points apart on a 0 to 100 scale.
Output price
Llama 3.2 1B Instruct $0.201 against Phi 4 $0.14 per million output tokens, 1.4x apart.
Context window
Llama 3.2 1B Instruct takes 60K tokens, Phi 4 16K.

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
CategoryLlama 3.2 1B InstructBarsPhi 4Ties
Coding04
Intelligence01
Agentic work011 tie
Reasoning15
Math05
Knowledge05
General113
All shared boards2341 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Llama 3.2 1B Instruct and Phi 4
BenchmarkLlama 3.2 1B InstructPhi 4Leader
LiveCodeBench (Artificial Analysis run)1.9%23.1%Phi 4
Terminal-Bench Hard (Artificial Analysis run)0.0%3.8%Phi 4
LMArena Text: coding10701231Phi 4
LMArena Text: software and IT10561228Phi 4
Neither model has a result on the other 34 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Llama 3.2 1B Instruct and Phi 4
BenchmarkLlama 3.2 1B InstructPhi 4Leader
AA Intelligence Index4.85.9Phi 4
Epoch Capabilities IndexNot measured130.5Only Phi 4 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Llama 3.2 1B Instruct and Phi 4
BenchmarkLlama 3.2 1B InstructPhi 4Leader
τ²-Bench Telecom0.0%0.0%Tie
BALROG6.6%11.6%Phi 4
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index15
Reasoning benchmarks for Llama 3.2 1B Instruct and Phi 4
BenchmarkLlama 3.2 1B InstructPhi 4Leader
GPQA Diamond (Artificial Analysis run)19.6%57.5%Phi 4
Humanity's Last Exam (Artificial Analysis run)5.5%3.8%Llama 3.2 1B Instruct
GPQA Diamond (Epoch AI run)23.9%56.1%Phi 4
LMArena Text: hard prompts10441220Phi 4
LMArena Text: expert10071203Phi 4
LMArena Text: hard prompts in English10871230Phi 4
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index05
Math benchmarks for Llama 3.2 1B Instruct and Phi 4
BenchmarkLlama 3.2 1B InstructPhi 4Leader
AA Math Index0.018.0Phi 4
AIME 2025 (Artificial Analysis run)0.0%18.0%Phi 4
OTIS Mock AIME0.6%13.8%Phi 4
MATH level 5Not measured64.9%Only Phi 4 measured
LMArena Text: math10861246Phi 4
LMArena Text: mathematical work10981254Phi 4
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for Llama 3.2 1B Instruct and Phi 4
BenchmarkLlama 3.2 1B InstructPhi 4Leader
MMLU Pro (Artificial Analysis run)20.0%71.4%Phi 4
MMLUNot measured84.8%Only Phi 4 measured
LMArena Text: science10551206Phi 4
LMArena Text: medicine and healthcare10091202Phi 4
LMArena Text: legal and government10711241Phi 4
LMArena Text: business and finance10001199Phi 4
Neither model has a result on the other 11 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Llama 3.2 1B Instruct and Phi 4
BenchmarkLlama 3.2 1B InstructPhi 4Leader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index113
General benchmarks for Llama 3.2 1B Instruct and Phi 4
BenchmarkLlama 3.2 1B InstructPhi 4Leader
IFBench22.8%23.5%Phi 4
Long context reasoning (AA-LCR)6.7%0.0%Llama 3.2 1B Instruct
Creative writing (Lech Mazur)Not measured62.6%Only Phi 4 measured
LMArena Text10551217Phi 4
LMArena Text: instruction following10311201Phi 4
LMArena Text: creative writing10331181Phi 4
LMArena Text: English11171231Phi 4
LMArena Text: non-English9731197Phi 4
LMArena Text: Chinese9591212Phi 4
LMArena Text: German10141222Phi 4
LMArena Text: JapaneseNot measured1158Only Phi 4 measured
LMArena Text: KoreanNot measured1151Only Phi 4 measured
LMArena Text: FrenchNot measured1224Only Phi 4 measured
LMArena Text: SpanishNot measured1234Only Phi 4 measured
LMArena Text: Russian9411209Phi 4
LMArena Text: multi-turn10301206Phi 4
LMArena Text: longer queries10501217Phi 4
LMArena Text: writing and language10301198Phi 4
LMArena Text: entertainment and media10251162Phi 4
Neither model has a result on the other 27 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Llama 3.2 1B Instruct and Phi 4
BenchmarkLlama 3.2 1B InstructPhi 4Leader
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

Llama 3.2 1B Instruct$0.0001Fits in one request
Phi 4$0.0001Fits in one request

Llama 3.2 1B Instruct costs less

Repository review

50K input + 3K output tokens

Llama 3.2 1B Instruct$0.0020Fits in one request
Phi 4$0.0039Exceeds the context window

Llama 3.2 1B Instruct costs less

Agent loop

200K input + 10K output tokens

Llama 3.2 1B Instruct$0.0074Exceeds the context window
Phi 4$0.015Exceeds the context window

Llama 3.2 1B Instruct 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 Llama 3.2 1B Instruct and Phi 4
SpecificationMeta Llama 3.2 1B InstructMicrosoft Phi 4
MakerMeta LlamaMicrosoft
WeightsOpen weightsOpen weights
ReleasedSeptember 25, 2024January 10, 2025
Context window60K16K
Input $/Mtok$0.027$0.07
Output $/Mtok$0.201$0.14
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Llama 3.2 1B Instruct better than Phi 4 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Llama 3.2 1B Instruct has the edge where the context window is larger, 60K against 16K tokens, and where what matters is LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, Llama 3.2 1B Instruct or Phi 4?

Llama 3.2 1B Instruct costs $0.027 per million input tokens and $0.201 per million output tokens; Phi 4 costs $0.07 and $0.14. Cost per solved task is known for neither of them.

Which has the bigger context window, Llama 3.2 1B Instruct or Phi 4?

Llama 3.2 1B Instruct, with 60K tokens against 16K.

How many benchmarks is the Llama 3.2 1B Instruct vs Phi 4 comparison based on?

37 benchmarks have a result for both models as of October 21, 2026. Llama 3.2 1B Instruct's coding index rests on 0 independent benchmarks and Phi 4's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next