Enter opens the highlighted result. Esc closes.

Mercury 2 vs Llama 3.2 1B Instruct

Mercury 2 leads Llama 3.2 1B Instruct on the Artificial Analysis Intelligence Index, 10.8 to 4.8, and Llama 3.2 1B Instruct costs 3.7x less per output token ($0.201 vs $0.75 per million). Updated October 21, 2026; 26 benchmarks have a result for both.

Replace Mercury 2 Replace Llama 3.2 1B Instruct
Mercury 2Inception
Coding
No data
Overall
No data
Output $/M
$0.75
26
Llama 3.2 1B InstructMeta Llama
Coding
No data
Overall
9.6
Output $/M
$0.201
0
vs boards won of 26 shared

Mercury 2 or Llama 3.2 1B Instruct: which to pick

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

Pick Mercury 2 for a larger context window (128K against 60K tokens).

Model AMercury 2InceptionNot benchmarked1 independent benchmarkNo cost per solved taskModel BLlama 3.2 1B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
26
Mercury 2 only
16
Llama 3.2 1B Instruct only
12
Like-for-like categories
6 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
Mercury 2 not benchmarked, Llama 3.2 1B Instruct not benchmarked.
Widest category
Agentic work, 70.8 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Mercury 2 70.8% against Llama 3.2 1B Instruct 0.0%, 70.8 points apart on a 0 to 100 scale.
Output price
Mercury 2 $0.75 against Llama 3.2 1B Instruct $0.201 per million output tokens, 3.7x apart.
Context window
Mercury 2 takes 128K 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
CategoryMercury 2BarsLlama 3.2 1B InstructTies
Coding30
Intelligence10
Agentic work10
Reasoning50
Knowledge30
General130
All shared boards260
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for Mercury 2 and Llama 3.2 1B Instruct
BenchmarkMercury 2Llama 3.2 1B InstructLeader
LMArena WebDev1171Not measuredOnly Mercury 2 measured
AA Coding Index31.1Not measuredOnly Mercury 2 measured
LiveCodeBench (Artificial Analysis run)Not measured1.9%Only Llama 3.2 1B Instruct measured
SciCode37.7%Not measuredOnly Mercury 2 measured
Terminal-Bench Hard (Artificial Analysis run)26.5%0.0%Mercury 2
WeirdML43.2%Not measuredOnly Mercury 2 measured
ALE-Bench785.6Not measuredOnly Mercury 2 measured
LMArena Text: coding13901070Mercury 2
LMArena Text: software and IT13851056Mercury 2
LMArena WebDev: React1160Not measuredOnly Mercury 2 measured
LMArena WebDev: HTML1199Not measuredOnly Mercury 2 measured
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Mercury 2 and Llama 3.2 1B Instruct
BenchmarkMercury 2Llama 3.2 1B InstructLeader
AA Intelligence Index10.84.8Mercury 2
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 Mercury 2 and Llama 3.2 1B Instruct
BenchmarkMercury 2Llama 3.2 1B InstructLeader
AA Agentic Index1.6Not measuredOnly Mercury 2 measured
τ²-Bench Telecom70.8%0.0%Mercury 2
BALROGNot measured6.6%Only Llama 3.2 1B Instruct measured
Berkeley Function Calling Leaderboard (BFCL)Not measured10.8%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 index50
Reasoning benchmarks for Mercury 2 and Llama 3.2 1B Instruct
BenchmarkMercury 2Llama 3.2 1B InstructLeader
GPQA Diamond (Artificial Analysis run)77.0%19.6%Mercury 2
Humanity's Last Exam (Artificial Analysis run)17.1%5.5%Mercury 2
GPQA Diamond (Epoch AI run)Not measured23.9%Only Llama 3.2 1B Instruct measured
LMArena Text: hard prompts13621044Mercury 2
LMArena Text: expert13581007Mercury 2
LMArena Text: hard prompts in English13741087Mercury 2
Neither model has a result on the other 16 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Math benchmarks for Mercury 2 and Llama 3.2 1B Instruct
BenchmarkMercury 2Llama 3.2 1B InstructLeader
AA Math IndexNot measured0.0Only Llama 3.2 1B Instruct measured
AIME 2025 (Artificial Analysis run)Not measured0.0%Only Llama 3.2 1B Instruct measured
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 index30
Knowledge benchmarks for Mercury 2 and Llama 3.2 1B Instruct
BenchmarkMercury 2Llama 3.2 1B InstructLeader
MMLU Pro (Artificial Analysis run)Not measured20.0%Only Llama 3.2 1B Instruct measured
LMArena Text: science13431055Mercury 2
LMArena Text: medicine and healthcare13631009Mercury 2
LMArena Text: legal and governmentNot measured1071Only Llama 3.2 1B Instruct measured
LMArena Text: business and finance13491000Mercury 2
Neither model has a result on the other 13 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Mercury 2 and Llama 3.2 1B Instruct
BenchmarkMercury 2Llama 3.2 1B InstructLeader
Design Arena: websites1036Not measuredOnly Mercury 2 measured
Design Arena: UI components998Not measuredOnly Mercury 2 measured
Design Arena: game dev985Not measuredOnly Mercury 2 measured
Design Arena: data viz1009Not measuredOnly Mercury 2 measured
Design Arena: 3D983Not measuredOnly Mercury 2 measured
Design Arena: all code categories1022Not measuredOnly Mercury 2 measured
Design Arena: SVG998Not measuredOnly Mercury 2 measured
Design Arena: ASCII art988Not measuredOnly Mercury 2 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
General benchmarks for Mercury 2 and Llama 3.2 1B Instruct
BenchmarkMercury 2Llama 3.2 1B InstructLeader
IFBench69.8%22.8%Mercury 2
Long context reasoning (AA-LCR)43.7%6.7%Mercury 2
LMArena Text13541055Mercury 2
LMArena Text: instruction following13281031Mercury 2
LMArena Text: creative writing12861033Mercury 2
LMArena Text: English13781117Mercury 2
LMArena Text: non-English1330973Mercury 2
LMArena Text: Chinese1414959Mercury 2
LMArena Text: GermanNot measured1014Only Llama 3.2 1B Instruct measured
LMArena Text: Russian1304941Mercury 2
LMArena Text: multi-turn13571030Mercury 2
LMArena Text: longer queries13291050Mercury 2
LMArena Text: writing and language13001030Mercury 2
LMArena Text: entertainment and media13141025Mercury 2
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 Mercury 2 and Llama 3.2 1B Instruct
BenchmarkMercury 2Llama 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

Mercury 2$0.0006Fits 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

Mercury 2$0.015Fits 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

Mercury 2$0.058Exceeds the context window
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 Mercury 2 and Llama 3.2 1B Instruct
SpecificationInception Mercury 2Meta Llama 3.2 1B Instruct
MakerInceptionMeta Llama
WeightsNo public weights listedOpen weights
ReleasedMarch 4, 2026September 25, 2024
Context window128K60K
Input $/Mtok$0.25$0.027
Output $/Mtok$0.75$0.201
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Mercury 2 better than Llama 3.2 1B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Mercury 2 for a larger context window (128K against 60K tokens).

Which is cheaper, Mercury 2 or Llama 3.2 1B Instruct?

Mercury 2 costs $0.25 per million input tokens and $0.75 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, Mercury 2 or Llama 3.2 1B Instruct?

Mercury 2, with 128K tokens against 60K.

How many benchmarks is the Mercury 2 vs Llama 3.2 1B Instruct comparison based on?

26 benchmarks have a result for both models as of October 21, 2026. Mercury 2'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