Enter opens the highlighted result. Esc closes.

Llama 3.1 70B Instruct vs Llama 3.1 8B Instruct

Llama 3.1 8B Instruct leads Llama 3.1 70B Instruct on the Artificial Analysis Intelligence Index, 6.9 to 6.6, and Llama 3.1 8B Instruct costs 7.0x less per output token ($0.08 vs $0.56 per million). Updated October 21, 2026; 46 benchmarks have a result for both.

Replace Llama 3.1 70B Instruct Replace Llama 3.1 8B Instruct
Llama 3.1 70B InstructMeta Llama
Coding
No data
Overall
24.3
Output $/M
$0.56
41
Llama 3.1 8B InstructMeta Llama
Coding
No data
Overall
17.9
Output $/M
$0.08
5
vs boards won of 46 shared

Llama 3.1 70B Instruct or Llama 3.1 8B Instruct: which to pick

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

Pick Llama 3.1 70B Instruct for work measured by AA Intelligence Index or τ²-Bench Telecom, where it leads.

Model ALlama 3.1 70B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved taskModel BLlama 3.1 8B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
46
Llama 3.1 70B Instruct only
1
Llama 3.1 8B Instruct only
5
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 3.1 70B Instruct not benchmarked, Llama 3.1 8B Instruct not benchmarked.
Widest category
Knowledge, 15.8 points apart on average over 6 shared benchmarks.
Widest single gap
MMLU: Llama 3.1 70B Instruct 80.1% against Llama 3.1 8B Instruct 56.1%, 24.0 points apart on a 0 to 100 scale.
Output price
Llama 3.1 70B Instruct $0.56 against Llama 3.1 8B Instruct $0.08 per million output tokens, 7.0x apart.
Context window
Both take 131K tokens.

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 3.1 70B InstructBarsLlama 3.1 8B InstructTies
Coding50
Intelligence11
Agentic work11
Reasoning51
Math42
Knowledge60
General190
All shared boards415
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
Coding benchmarks for Llama 3.1 70B Instruct and Llama 3.1 8B Instruct
BenchmarkLlama 3.1 70B InstructLlama 3.1 8B InstructLeader
AA Coding IndexNot measured5.4Only Llama 3.1 8B Instruct measured
LiveCodeBench (Artificial Analysis run)23.2%11.6%Llama 3.1 70B Instruct
Terminal-Bench Hard (Artificial Analysis run)3.0%0.8%Llama 3.1 70B Instruct
WeirdML9.0%1.7%Llama 3.1 70B Instruct
LMArena Text: coding12601195Llama 3.1 70B Instruct
LMArena Text: software and IT12601195Llama 3.1 70B Instruct
Neither model has a result on the other 33 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Llama 3.1 70B Instruct and Llama 3.1 8B Instruct
BenchmarkLlama 3.1 70B InstructLlama 3.1 8B InstructLeader
AA Intelligence Index6.66.9Llama 3.1 8B Instruct
Epoch Capabilities Index125.9116.5Llama 3.1 70B Instruct
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for Llama 3.1 70B Instruct and Llama 3.1 8B Instruct
BenchmarkLlama 3.1 70B InstructLlama 3.1 8B InstructLeader
τ²-Bench Telecom15.2%16.4%Llama 3.1 8B Instruct
BALROG27.9%15.1%Llama 3.1 70B Instruct
TheAgentCompany6.9%Not measuredOnly Llama 3.1 70B Instruct measured
Berkeley Function Calling Leaderboard (BFCL)Not measured25.8%Only Llama 3.1 8B Instruct measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index51
Reasoning benchmarks for Llama 3.1 70B Instruct and Llama 3.1 8B Instruct
BenchmarkLlama 3.1 70B InstructLlama 3.1 8B InstructLeader
GPQA Diamond (Artificial Analysis run)40.9%25.9%Llama 3.1 70B Instruct
Humanity's Last Exam (Artificial Analysis run)4.5%5.3%Llama 3.1 8B Instruct
GPQA Diamond (Epoch AI run)44.2%27.0%Llama 3.1 70B Instruct
LMArena Text: hard prompts12411175Llama 3.1 70B Instruct
LMArena Text: expert12091144Llama 3.1 70B Instruct
LMArena Text: hard prompts in English12611196Llama 3.1 70B Instruct
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index42
Math benchmarks for Llama 3.1 70B Instruct and Llama 3.1 8B Instruct
BenchmarkLlama 3.1 70B InstructLlama 3.1 8B InstructLeader
AA Math Index4.04.3Llama 3.1 8B Instruct
AIME 2025 (Artificial Analysis run)4.0%4.3%Llama 3.1 8B Instruct
OTIS Mock AIME3.6%1.7%Llama 3.1 70B Instruct
MATH level 536.7%22.9%Llama 3.1 70B Instruct
GSM8KNot measured82.4%Only Llama 3.1 8B Instruct measured
LMArena Text: math12521179Llama 3.1 70B Instruct
LMArena Text: mathematical work12531180Llama 3.1 70B Instruct
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
Knowledge benchmarks for Llama 3.1 70B Instruct and Llama 3.1 8B Instruct
BenchmarkLlama 3.1 70B InstructLlama 3.1 8B InstructLeader
MMLU Pro (Artificial Analysis run)67.6%47.6%Llama 3.1 70B Instruct
MMLU80.1%56.1%Llama 3.1 70B Instruct
LMArena Text: science12761193Llama 3.1 70B Instruct
LMArena Text: medicine and healthcare12571182Llama 3.1 70B Instruct
LMArena Text: legal and government12831206Llama 3.1 70B Instruct
LMArena Text: business and finance12351166Llama 3.1 70B Instruct
Neither model has a result on the other 12 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Llama 3.1 70B Instruct and Llama 3.1 8B Instruct
BenchmarkLlama 3.1 70B InstructLlama 3.1 8B InstructLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index190
General benchmarks for Llama 3.1 70B Instruct and Llama 3.1 8B Instruct
BenchmarkLlama 3.1 70B InstructLlama 3.1 8B InstructLeader
IFBench34.4%28.6%Llama 3.1 70B Instruct
Long context reasoning (AA-LCR)Not measured18.0%Only Llama 3.1 8B Instruct measured
DTBench60.0%50.9%Llama 3.1 70B Instruct
LMCA14.8%5.4%Llama 3.1 70B Instruct
PIQANot measured81.2%Only Llama 3.1 8B Instruct measured
LMArena Text12611187Llama 3.1 70B Instruct
LMArena Text: instruction following12311159Llama 3.1 70B Instruct
LMArena Text: creative writing12321154Llama 3.1 70B Instruct
LMArena Text: English12941218Llama 3.1 70B Instruct
LMArena Text: non-English12191148Llama 3.1 70B Instruct
LMArena Text: Chinese12151151Llama 3.1 70B Instruct
LMArena Text: German12221144Llama 3.1 70B Instruct
LMArena Text: Japanese11321061Llama 3.1 70B Instruct
LMArena Text: Korean11401053Llama 3.1 70B Instruct
LMArena Text: French12621178Llama 3.1 70B Instruct
LMArena Text: Spanish12531169Llama 3.1 70B Instruct
LMArena Text: Russian12341158Llama 3.1 70B Instruct
LMArena Text: multi-turn12561172Llama 3.1 70B Instruct
LMArena Text: longer queries12411181Llama 3.1 70B Instruct
LMArena Text: writing and language12361162Llama 3.1 70B Instruct
LMArena Text: entertainment and media12301145Llama 3.1 70B Instruct
Neither model has a result on the other 25 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Llama 3.1 70B Instruct and Llama 3.1 8B Instruct
BenchmarkLlama 3.1 70B InstructLlama 3.1 8B 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 3.1 70B Instruct$0.0008Fits in one request
Llama 3.1 8B Instruct$0.0001Fits in one request

Llama 3.1 8B Instruct costs less

Repository review

50K input + 3K output tokens

Llama 3.1 70B Instruct$0.030Fits in one request
Llama 3.1 8B Instruct$0.0027Fits in one request

Llama 3.1 8B Instruct costs less

Agent loop

200K input + 10K output tokens

Llama 3.1 70B Instruct$0.118Exceeds the context window
Llama 3.1 8B Instruct$0.011Exceeds the context window

Llama 3.1 8B 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 3.1 70B Instruct and Llama 3.1 8B Instruct
SpecificationMeta Llama 3.1 70B InstructMeta Llama 3.1 8B Instruct
MakerMeta LlamaMeta Llama
WeightsOpen weightsOpen weights
ReleasedJuly 23, 2024July 23, 2024
Context window131K131K
Input $/Mtok$0.56$0.05
Output $/Mtok$0.56$0.08
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Llama 3.1 70B Instruct better than Llama 3.1 8B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Llama 3.1 70B Instruct for work measured by AA Intelligence Index or τ²-Bench Telecom, where it leads.

Which is cheaper, Llama 3.1 70B Instruct or Llama 3.1 8B Instruct?

Llama 3.1 70B Instruct costs $0.56 per million input tokens and $0.56 per million output tokens; Llama 3.1 8B Instruct costs $0.05 and $0.08. Cost per solved task is known for neither of them.

Which has the bigger context window, Llama 3.1 70B Instruct or Llama 3.1 8B Instruct?

Neither: both take 131K tokens.

How many benchmarks is the Llama 3.1 70B Instruct vs Llama 3.1 8B Instruct comparison based on?

46 benchmarks have a result for both models as of October 21, 2026. Llama 3.1 70B Instruct's coding index rests on 0 independent benchmarks and Llama 3.1 8B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next