Enter opens the highlighted result. Esc closes.

GPT-5.1-Codex-Mini vs Llama 3.2 1B Instruct

Updated October 21, 2026. 11 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-5.1-Codex-Mini Replace Llama 3.2 1B Instruct
GPT-5.1-Codex-MiniOpenAI
Coding
No data
Overall
20.4
Output $/M
$2.00
11
Llama 3.2 1B InstructMeta Llama
Coding
No data
Overall
4.8
Output $/M
$0.201
0
vs boards won of 11 shared

Decision reading

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

GPT-5.1-Codex-Mini has the edge where the context window is larger, 400K against 60K tokens.

Model AGPT-5.1-Codex-MiniOpenAINot benchmarked1 independent benchmarkNo cost per solved taskModel BLlama 3.2 1B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
11
GPT-5.1-Codex-Mini only
11
Llama 3.2 1B Instruct only
26
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
GPT-5.1-Codex-Mini not benchmarked, Llama 3.2 1B Instruct not benchmarked.
Widest category
Math, 91.7 points apart on average over 2 shared benchmarks.
Widest single gap
AA Math Index: GPT-5.1-Codex-Mini 91.7 against Llama 3.2 1B Instruct 0.0, 91.7 points apart on a 0 to 100 scale.
Output price
GPT-5.1-Codex-Mini $2.00 against Llama 3.2 1B Instruct $0.201 per million output tokens, 10.0x apart.
Context window
GPT-5.1-Codex-Mini takes 400K tokens, Llama 3.2 1B Instruct 60K.

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
CategoryGPT-5.1-Codex-MiniBarsLlama 3.2 1B InstructTies
Coding20
Intelligence10
Agentic work10
Reasoning20
Math20
Knowledge10
General20
All shared boards110
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
Coding benchmarks for GPT-5.1-Codex-Mini and Llama 3.2 1B Instruct
BenchmarkGPT-5.1-Codex-MiniLlama 3.2 1B InstructLeader
LMArena WebDev1244Not measuredOnly GPT-5.1-Codex-Mini measured
LiveCodeBench (Artificial Analysis run)83.6%1.9%GPT-5.1-Codex-Mini
Terminal-Bench Hard (Artificial Analysis run)33.3%0.0%GPT-5.1-Codex-Mini
Terminal-Bench61.6%Not measuredOnly GPT-5.1-Codex-Mini measured
LMArena Text: codingNot measured1070Only Llama 3.2 1B Instruct measured
LMArena Text: software and ITNot measured1056Only Llama 3.2 1B Instruct measured
LMArena WebDev: HTML1253Not measuredOnly GPT-5.1-Codex-Mini measured
Neither model has a result on the other 31 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GPT-5.1-Codex-Mini and Llama 3.2 1B Instruct
BenchmarkGPT-5.1-Codex-MiniLlama 3.2 1B InstructLeader
AA Intelligence Index20.44.8GPT-5.1-Codex-Mini
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-5.1-Codex-Mini and Llama 3.2 1B Instruct
BenchmarkGPT-5.1-Codex-MiniLlama 3.2 1B InstructLeader
τ²-Bench Telecom62.9%0.0%GPT-5.1-Codex-Mini
BALROGNot measured6.6%Only Llama 3.2 1B Instruct measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
Reasoning benchmarks for GPT-5.1-Codex-Mini and Llama 3.2 1B Instruct
BenchmarkGPT-5.1-Codex-MiniLlama 3.2 1B InstructLeader
GPQA Diamond (Artificial Analysis run)81.3%19.6%GPT-5.1-Codex-Mini
Humanity's Last Exam (Artificial Analysis run)18.5%5.5%GPT-5.1-Codex-Mini
GPQA Diamond (Epoch AI run)Not measured23.9%Only Llama 3.2 1B Instruct measured
LMArena Text: hard promptsNot measured1044Only Llama 3.2 1B Instruct measured
LMArena Text: expertNot measured1007Only Llama 3.2 1B Instruct measured
LMArena Text: hard prompts in EnglishNot measured1087Only Llama 3.2 1B Instruct measured
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for GPT-5.1-Codex-Mini and Llama 3.2 1B Instruct
BenchmarkGPT-5.1-Codex-MiniLlama 3.2 1B InstructLeader
AA Math Index91.70.0GPT-5.1-Codex-Mini
AIME 2025 (Artificial Analysis run)91.7%0.0%GPT-5.1-Codex-Mini
OTIS Mock AIMENot measured0.6%Only Llama 3.2 1B Instruct measured
LMArena Text: mathNot measured1086Only Llama 3.2 1B Instruct measured
LMArena Text: mathematical workNot measured1098Only Llama 3.2 1B Instruct measured
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
Knowledge benchmarks for GPT-5.1-Codex-Mini and Llama 3.2 1B Instruct
BenchmarkGPT-5.1-Codex-MiniLlama 3.2 1B InstructLeader
MMLU Pro (Artificial Analysis run)82.0%20.0%GPT-5.1-Codex-Mini
LMArena Text: scienceNot measured1055Only Llama 3.2 1B Instruct measured
LMArena Text: medicine and healthcareNot measured1009Only Llama 3.2 1B Instruct measured
LMArena Text: legal and governmentNot measured1071Only Llama 3.2 1B Instruct measured
LMArena Text: business and financeNot measured1000Only Llama 3.2 1B Instruct measured
Neither model has a result on the other 12 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GPT-5.1-Codex-Mini and Llama 3.2 1B Instruct
BenchmarkGPT-5.1-Codex-MiniLlama 3.2 1B InstructLeader
Design Arena: websites1111Not measuredOnly GPT-5.1-Codex-Mini measured
Design Arena: UI components1081Not measuredOnly GPT-5.1-Codex-Mini measured
Design Arena: game dev1092Not measuredOnly GPT-5.1-Codex-Mini measured
Design Arena: data viz1096Not measuredOnly GPT-5.1-Codex-Mini measured
Design Arena: 3D988Not measuredOnly GPT-5.1-Codex-Mini measured
Design Arena: all code categories1094Not measuredOnly GPT-5.1-Codex-Mini measured
Design Arena: SVG978Not measuredOnly GPT-5.1-Codex-Mini measured
Design Arena: ASCII art1104Not measuredOnly GPT-5.1-Codex-Mini measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index20
General benchmarks for GPT-5.1-Codex-Mini and Llama 3.2 1B Instruct
BenchmarkGPT-5.1-Codex-MiniLlama 3.2 1B InstructLeader
IFBench67.9%22.8%GPT-5.1-Codex-Mini
Long context reasoning (AA-LCR)66.7%6.7%GPT-5.1-Codex-Mini
LMArena TextNot measured1055Only Llama 3.2 1B Instruct measured
LMArena Text: instruction followingNot measured1031Only Llama 3.2 1B Instruct measured
LMArena Text: creative writingNot measured1033Only Llama 3.2 1B Instruct measured
LMArena Text: EnglishNot measured1117Only Llama 3.2 1B Instruct measured
LMArena Text: non-EnglishNot measured973Only Llama 3.2 1B Instruct measured
LMArena Text: ChineseNot measured959Only Llama 3.2 1B Instruct measured
LMArena Text: GermanNot measured1014Only Llama 3.2 1B Instruct measured
LMArena Text: RussianNot measured941Only Llama 3.2 1B Instruct measured
LMArena Text: multi-turnNot measured1030Only Llama 3.2 1B Instruct measured
LMArena Text: longer queriesNot measured1050Only Llama 3.2 1B Instruct measured
LMArena Text: writing and languageNot measured1030Only Llama 3.2 1B Instruct measured
LMArena Text: entertainment and mediaNot measured1025Only Llama 3.2 1B Instruct measured
Neither model has a result on the other 32 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.1-Codex-Mini and Llama 3.2 1B Instruct
BenchmarkGPT-5.1-Codex-MiniLlama 3.2 1B InstructLeader
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

GPT-5.1-Codex-Mini$0.0013Fits in one request
Llama 3.2 1B Instruct$0.0001Fits in one request

Llama 3.2 1B Instruct costs less

Repository review

50K input + 3K output tokens

GPT-5.1-Codex-Mini$0.018Fits in one request
Llama 3.2 1B Instruct$0.0020Fits in one request

Llama 3.2 1B Instruct costs less

Agent loop

200K input + 10K output tokens

GPT-5.1-Codex-Mini$0.070Fits in one request
Llama 3.2 1B Instruct$0.0074Exceeds 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 GPT-5.1-Codex-Mini and Llama 3.2 1B Instruct
SpecificationOpenAI GPT-5.1-Codex-MiniMeta Llama 3.2 1B Instruct
MakerOpenAIMeta Llama
WeightsNo public weights listedOpen weights
ReleasedNovember 13, 2025September 25, 2024
Context window400K60K
Input $/Mtok$0.25$0.027
Output $/Mtok$2.00$0.201
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.1-Codex-Mini better than Llama 3.2 1B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. GPT-5.1-Codex-Mini has the edge where the context window is larger, 400K against 60K tokens.

Which is cheaper, GPT-5.1-Codex-Mini or Llama 3.2 1B Instruct?

GPT-5.1-Codex-Mini costs $0.25 per million input tokens and $2.00 per million output tokens; Llama 3.2 1B Instruct costs $0.027 and $0.201. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-5.1-Codex-Mini or Llama 3.2 1B Instruct?

GPT-5.1-Codex-Mini, with 400K tokens against 60K.

How many benchmarks is the GPT-5.1-Codex-Mini vs Llama 3.2 1B Instruct comparison based on?

11 benchmarks have a result for both models as of October 21, 2026. GPT-5.1-Codex-Mini's coding index rests on 1 independent benchmark and Llama 3.2 1B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next