Enter opens the highlighted result. Esc closes.

Llama 3.1 70B Instruct vs Hy3 preview

Hy3 preview leads Llama 3.1 70B Instruct on the Artificial Analysis Intelligence Index, 25.3 to 6.6, at about the same output price ($0.60 vs $0.56 per million). Updated October 21, 2026; 30 benchmarks have a result for both.

Replace Llama 3.1 70B Instruct Replace Hy3 preview
Llama 3.1 70B InstructMeta Llama
Coding
No data
Overall
24.3
Output $/M
$0.56
0
Hy3 previewTencent
Coding
No data
Overall
No data
Output $/M
$0.60
30
vs boards won of 30 shared

Llama 3.1 70B Instruct or Hy3 preview: 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 output tokens 1.1x cheaper ($0.56 vs $0.60 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.

Model ALlama 3.1 70B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved taskModel BHy3 previewTencentNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
30
Llama 3.1 70B Instruct only
17
Hy3 preview only
6
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, Hy3 preview not benchmarked.
Widest category
Agentic work, 77.5 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Llama 3.1 70B Instruct 15.2% against Hy3 preview 92.7%, 77.5 points apart on a 0 to 100 scale.
Output price
Llama 3.1 70B Instruct $0.56 against Hy3 preview $0.60 per million output tokens, 1.1x apart.
Context window
Llama 3.1 70B Instruct takes 131K tokens, Hy3 preview 262K.

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 InstructBarsHy3 previewTies
Coding03
Intelligence01
Agentic work01
Reasoning05
Math02
Knowledge04
General014
All shared boards030
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for Llama 3.1 70B Instruct and Hy3 preview
BenchmarkLlama 3.1 70B InstructHy3 previewLeader
LMArena WebDevNot measured1357Only Hy3 preview measured
AA Coding IndexNot measured58.8Only Hy3 preview measured
LiveCodeBench (Artificial Analysis run)23.2%Not measuredOnly Llama 3.1 70B Instruct measured
Terminal-Bench Hard (Artificial Analysis run)3.0%34.1%Hy3 preview
WeirdML9.0%Not measuredOnly Llama 3.1 70B Instruct measured
LMArena Text: coding12601421Hy3 preview
LMArena Text: software and IT12601423Hy3 preview
LMArena WebDev: ReactNot measured1349Only Hy3 preview measured
LMArena WebDev: HTMLNot measured1356Only Hy3 preview measured
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Llama 3.1 70B Instruct and Hy3 preview
BenchmarkLlama 3.1 70B InstructHy3 previewLeader
AA Intelligence Index6.625.3Hy3 preview
Epoch Capabilities Index125.9Not measuredOnly Llama 3.1 70B Instruct measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Llama 3.1 70B Instruct and Hy3 preview
BenchmarkLlama 3.1 70B InstructHy3 previewLeader
AA Agentic IndexNot measured24.1Only Hy3 preview measured
τ²-Bench Telecom15.2%92.7%Hy3 preview
BALROG27.9%Not measuredOnly Llama 3.1 70B Instruct measured
TheAgentCompany6.9%Not measuredOnly Llama 3.1 70B Instruct measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Llama 3.1 70B Instruct and Hy3 preview
BenchmarkLlama 3.1 70B InstructHy3 previewLeader
GPQA Diamond (Artificial Analysis run)40.9%86.7%Hy3 preview
Humanity's Last Exam (Artificial Analysis run)4.5%27.8%Hy3 preview
GPQA Diamond (Epoch AI run)44.2%Not measuredOnly Llama 3.1 70B Instruct measured
LMArena Text: hard prompts12411413Hy3 preview
LMArena Text: expert12091422Hy3 preview
LMArena Text: hard prompts in English12611416Hy3 preview
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Llama 3.1 70B Instruct and Hy3 preview
BenchmarkLlama 3.1 70B InstructHy3 previewLeader
AA Math Index4.0Not measuredOnly Llama 3.1 70B Instruct measured
AIME 2025 (Artificial Analysis run)4.0%Not measuredOnly Llama 3.1 70B Instruct measured
OTIS Mock AIME3.6%Not measuredOnly Llama 3.1 70B Instruct measured
MATH level 536.7%Not measuredOnly Llama 3.1 70B Instruct measured
LMArena Text: math12521424Hy3 preview
LMArena Text: mathematical work12531442Hy3 preview
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for Llama 3.1 70B Instruct and Hy3 preview
BenchmarkLlama 3.1 70B InstructHy3 previewLeader
MMLU Pro (Artificial Analysis run)67.6%Not measuredOnly Llama 3.1 70B Instruct measured
MMLU80.1%Not measuredOnly Llama 3.1 70B Instruct measured
LMArena Text: science12761416Hy3 preview
LMArena Text: medicine and healthcare12571405Hy3 preview
LMArena Text: legal and government12831430Hy3 preview
LMArena Text: business and finance12351397Hy3 preview
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 Hy3 preview
BenchmarkLlama 3.1 70B InstructHy3 previewLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index014
General benchmarks for Llama 3.1 70B Instruct and Hy3 preview
BenchmarkLlama 3.1 70B InstructHy3 previewLeader
IFBench34.4%63.1%Hy3 preview
Long context reasoning (AA-LCR)Not measured64.7%Only Hy3 preview measured
DTBench60.0%Not measuredOnly Llama 3.1 70B Instruct measured
LMCA14.8%Not measuredOnly Llama 3.1 70B Instruct measured
LMArena Text12611401Hy3 preview
LMArena Text: instruction following12311383Hy3 preview
LMArena Text: creative writing12321339Hy3 preview
LMArena Text: English12941409Hy3 preview
LMArena Text: non-English12191390Hy3 preview
LMArena Text: Chinese12151435Hy3 preview
LMArena Text: German1222Not measuredOnly Llama 3.1 70B Instruct measured
LMArena Text: Japanese1132Not measuredOnly Llama 3.1 70B Instruct measured
LMArena Text: Korean1140Not measuredOnly Llama 3.1 70B Instruct measured
LMArena Text: French12621425Hy3 preview
LMArena Text: Spanish12531399Hy3 preview
LMArena Text: Russian12341399Hy3 preview
LMArena Text: multi-turn12561411Hy3 preview
LMArena Text: longer queries12411402Hy3 preview
LMArena Text: writing and language12361370Hy3 preview
LMArena Text: entertainment and media12301352Hy3 preview
Neither model has a result on the other 26 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 Hy3 preview
BenchmarkLlama 3.1 70B InstructHy3 previewLeader
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
Hy3 preview$0.0005Fits in one request

Hy3 preview costs less

Repository review

50K input + 3K output tokens

Llama 3.1 70B Instruct$0.030Fits in one request
Hy3 preview$0.011Fits in one request

Hy3 preview costs less

Agent loop

200K input + 10K output tokens

Llama 3.1 70B Instruct$0.118Exceeds the context window
Hy3 preview$0.042Fits in one request

Hy3 preview 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 Hy3 preview
SpecificationMeta Llama 3.1 70B InstructTencent Hy3 preview
MakerMeta LlamaTencent
WeightsOpen weightsOpen weights
ReleasedJuly 23, 2024April 22, 2026
Context window131K262K
Input $/Mtok$0.56$0.18
Output $/Mtok$0.56$0.60
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Llama 3.1 70B Instruct better than Hy3 preview for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Llama 3.1 70B Instruct for output tokens 1.1x cheaper ($0.56 vs $0.60 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.

Which is cheaper, Llama 3.1 70B Instruct or Hy3 preview?

Llama 3.1 70B Instruct costs $0.56 per million input tokens and $0.56 per million output tokens; Hy3 preview costs $0.18 and $0.60. Cost per solved task is known for neither of them.

Which has the bigger context window, Llama 3.1 70B Instruct or Hy3 preview?

Hy3 preview, with 262K tokens against 131K.

How many benchmarks is the Llama 3.1 70B Instruct vs Hy3 preview comparison based on?

30 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 Hy3 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next