Enter opens the highlighted result. Esc closes.

Llama 3.2 1B Instruct vs Qwen2.5 72B Instruct

Qwen2.5 72B Instruct leads Llama 3.2 1B Instruct on the Artificial Analysis Intelligence Index, 7.7 to 4.8, and Llama 3.2 1B Instruct costs 2.0x less per output token ($0.201 vs $0.40 per million). Updated October 21, 2026; 36 benchmarks have a result for both.

Replace Llama 3.2 1B Instruct Replace Qwen2.5 72B Instruct
Llama 3.2 1B InstructMeta Llama
Coding
No data
Overall
9.6
Output $/M
$0.201
1
Qwen2.5 72B InstructQwen
Coding
No data
Overall
26.5
Output $/M
$0.40
35
vs boards won of 36 shared

Llama 3.2 1B Instruct or Qwen2.5 72B Instruct: which to pick

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

Pick Llama 3.2 1B Instruct for output tokens 2.0x cheaper ($0.201 vs $0.40 per million) and a larger context window (60K against 33K tokens).

Model ALlama 3.2 1B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen2.5 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
36
Llama 3.2 1B Instruct only
2
Qwen2.5 72B Instruct only
17
Like-for-like categories
7 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
Llama 3.2 1B Instruct not benchmarked, Qwen2.5 72B Instruct not benchmarked.
Widest category
Knowledge, 41.7 points apart on average over 5 shared benchmarks.
Widest single gap
MMLU Pro (Artificial Analysis run): Llama 3.2 1B Instruct 20.0% against Qwen2.5 72B Instruct 72.0%, 52.0 points apart on a 0 to 100 scale.
Output price
Llama 3.2 1B Instruct $0.201 against Qwen2.5 72B Instruct $0.40 per million output tokens, 2.0x apart.
Context window
Llama 3.2 1B Instruct takes 60K tokens, Qwen2.5 72B Instruct 33K.

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 InstructBarsQwen2.5 72B InstructTies
Coding04
Intelligence01
Agentic work02
Reasoning15
Math05
Knowledge05
General013
All shared boards135
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Llama 3.2 1B Instruct and Qwen2.5 72B Instruct
BenchmarkLlama 3.2 1B InstructQwen2.5 72B InstructLeader
LiveCodeBench (Artificial Analysis run)1.9%27.6%Qwen2.5 72B Instruct
Terminal-Bench Hard (Artificial Analysis run)0.0%4.5%Qwen2.5 72B Instruct
WeirdMLNot measured16.0%Only Qwen2.5 72B Instruct measured
LMArena Text: coding10701292Qwen2.5 72B Instruct
LMArena Text: software and IT10561292Qwen2.5 72B Instruct
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 Qwen2.5 72B Instruct
BenchmarkLlama 3.2 1B InstructQwen2.5 72B InstructLeader
AA Intelligence Index4.87.7Qwen2.5 72B Instruct
Epoch Capabilities IndexNot measured129.0Only Qwen2.5 72B Instruct measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Llama 3.2 1B Instruct and Qwen2.5 72B Instruct
BenchmarkLlama 3.2 1B InstructQwen2.5 72B InstructLeader
τ²-Bench Telecom0.0%34.5%Qwen2.5 72B Instruct
METR time horizonsNot measured35.8%Only Qwen2.5 72B Instruct measured
BALROG6.6%16.2%Qwen2.5 72B Instruct
TheAgentCompanyNot measured5.7%Only Qwen2.5 72B Instruct measured
Berkeley Function Calling Leaderboard (BFCL)10.8%Not measuredOnly Llama 3.2 1B Instruct measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index15
Reasoning benchmarks for Llama 3.2 1B Instruct and Qwen2.5 72B Instruct
BenchmarkLlama 3.2 1B InstructQwen2.5 72B InstructLeader
GPQA Diamond (Artificial Analysis run)19.6%49.1%Qwen2.5 72B Instruct
Humanity's Last Exam (Artificial Analysis run)5.5%3.6%Llama 3.2 1B Instruct
GPQA Diamond (Epoch AI run)23.9%49.1%Qwen2.5 72B Instruct
BIG-Bench HardNot measured79.8%Only Qwen2.5 72B Instruct measured
LMArena Text: hard prompts10441271Qwen2.5 72B Instruct
LMArena Text: expert10071245Qwen2.5 72B Instruct
LMArena Text: hard prompts in English10871279Qwen2.5 72B Instruct
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 Qwen2.5 72B Instruct
BenchmarkLlama 3.2 1B InstructQwen2.5 72B InstructLeader
AA Math Index0.014.0Qwen2.5 72B Instruct
AIME 2025 (Artificial Analysis run)0.0%14.0%Qwen2.5 72B Instruct
OTIS Mock AIME0.6%8.1%Qwen2.5 72B Instruct
MATH level 5Not measured63.2%Only Qwen2.5 72B Instruct measured
LMArena Text: math10861283Qwen2.5 72B Instruct
LMArena Text: mathematical work10981290Qwen2.5 72B Instruct
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 Qwen2.5 72B Instruct
BenchmarkLlama 3.2 1B InstructQwen2.5 72B InstructLeader
MMLU Pro (Artificial Analysis run)20.0%72.0%Qwen2.5 72B Instruct
MMLUNot measured85.3%Only Qwen2.5 72B Instruct measured
AI2 Reasoning ChallengeNot measured94.5%Only Qwen2.5 72B Instruct measured
LMArena Text: science10551275Qwen2.5 72B Instruct
LMArena Text: medicine and healthcare10091258Qwen2.5 72B Instruct
LMArena Text: legal and government10711288Qwen2.5 72B Instruct
LMArena Text: business and finance10001253Qwen2.5 72B Instruct
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 Qwen2.5 72B Instruct
BenchmarkLlama 3.2 1B InstructQwen2.5 72B InstructLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index013
General benchmarks for Llama 3.2 1B Instruct and Qwen2.5 72B Instruct
BenchmarkLlama 3.2 1B InstructQwen2.5 72B InstructLeader
IFBench22.8%36.9%Qwen2.5 72B Instruct
Long context reasoning (AA-LCR)6.7%Not measuredOnly Llama 3.2 1B Instruct measured
DTBenchNot measured62.9%Only Qwen2.5 72B Instruct measured
LMCANot measured13.4%Only Qwen2.5 72B Instruct measured
HellaSwagNot measured84.8%Only Qwen2.5 72B Instruct measured
WinoGrandeNot measured82.3%Only Qwen2.5 72B Instruct measured
PIQANot measured82.6%Only Qwen2.5 72B Instruct measured
LMArena Text10551269Qwen2.5 72B Instruct
LMArena Text: instruction following10311254Qwen2.5 72B Instruct
LMArena Text: creative writing10331221Qwen2.5 72B Instruct
LMArena Text: English11171283Qwen2.5 72B Instruct
LMArena Text: non-English9731252Qwen2.5 72B Instruct
LMArena Text: Chinese9591273Qwen2.5 72B Instruct
LMArena Text: German10141234Qwen2.5 72B Instruct
LMArena Text: JapaneseNot measured1180Only Qwen2.5 72B Instruct measured
LMArena Text: KoreanNot measured1188Only Qwen2.5 72B Instruct measured
LMArena Text: FrenchNot measured1280Only Qwen2.5 72B Instruct measured
LMArena Text: SpanishNot measured1255Only Qwen2.5 72B Instruct measured
LMArena Text: Russian9411264Qwen2.5 72B Instruct
LMArena Text: multi-turn10301272Qwen2.5 72B Instruct
LMArena Text: longer queries10501281Qwen2.5 72B Instruct
LMArena Text: writing and language10301247Qwen2.5 72B Instruct
LMArena Text: entertainment and media10251211Qwen2.5 72B Instruct
Neither model has a result on the other 23 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 Qwen2.5 72B Instruct
BenchmarkLlama 3.2 1B InstructQwen2.5 72B 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

Llama 3.2 1B Instruct$0.0001Fits in one request
Qwen2.5 72B Instruct$0.0006Fits 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
Qwen2.5 72B Instruct$0.019Exceeds 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
Qwen2.5 72B Instruct$0.076Exceeds 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 Qwen2.5 72B Instruct
SpecificationMeta Llama 3.2 1B InstructQwen2.5 72B Instruct
MakerMeta LlamaQwen
WeightsOpen weightsOpen weights
ReleasedSeptember 25, 2024September 19, 2024
Context window60K33K
Input $/Mtok$0.027$0.36
Output $/Mtok$0.201$0.40
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 Qwen2.5 72B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Llama 3.2 1B Instruct for output tokens 2.0x cheaper ($0.201 vs $0.40 per million) and a larger context window (60K against 33K tokens).

Which is cheaper, Llama 3.2 1B Instruct or Qwen2.5 72B Instruct?

Llama 3.2 1B Instruct costs $0.027 per million input tokens and $0.201 per million output tokens; Qwen2.5 72B Instruct costs $0.36 and $0.40. Cost per solved task is known for neither of them.

Which has the bigger context window, Llama 3.2 1B Instruct or Qwen2.5 72B Instruct?

Llama 3.2 1B Instruct, with 60K tokens against 33K.

How many benchmarks is the Llama 3.2 1B Instruct vs Qwen2.5 72B Instruct comparison based on?

36 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 Qwen2.5 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next