Enter opens the highlighted result. Esc closes.

R1 0528 vs Llama 3.1 70B Instruct

R1 0528 leads Llama 3.1 70B Instruct on the Artificial Analysis Intelligence Index, 13.1 to 6.6, and Llama 3.1 70B Instruct costs 3.9x less per output token ($0.56 vs $2.18 per million). Updated October 22, 2026; 41 benchmarks have a result for both.

Replace R1 0528 Replace Llama 3.1 70B Instruct
R1 0528DeepSeek
Coding
No data
Overall
46.8
Output $/M
$2.18
41
Llama 3.1 70B InstructMeta Llama
Coding
No data
Overall
24.3
Output $/M
$0.56
0
vs boards won of 41 shared

R1 0528 or Llama 3.1 70B Instruct: which to pick

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

Pick R1 0528 for a larger context window (164K against 131K tokens).

Model AR1 0528DeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BLlama 3.1 70B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
41
R1 0528 only
19
Llama 3.1 70B Instruct 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
R1 0528 not benchmarked, Llama 3.1 70B Instruct not benchmarked.
Widest category
Math, 53.1 points apart on average over 6 shared benchmarks.
Widest single gap
AA Math Index: R1 0528 76.0 against Llama 3.1 70B Instruct 4.0, 72.0 points apart on a 0 to 100 scale.
Output price
R1 0528 $2.18 against Llama 3.1 70B Instruct $0.56 per million output tokens, 3.9x apart.
Context window
R1 0528 takes 164K tokens, Llama 3.1 70B Instruct 131K.

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
CategoryR1 0528BarsLlama 3.1 70B InstructTies
Coding50
Intelligence10
Agentic work10
Reasoning60
Math60
Knowledge50
General170
All shared boards410
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
Coding benchmarks for R1 0528 and Llama 3.1 70B Instruct
BenchmarkR1 0528Llama 3.1 70B InstructLeader
Aider polyglot71.4%Not measuredOnly R1 0528 measured
LiveCodeBench (Artificial Analysis run)77.0%23.2%R1 0528
Terminal-Bench Hard (Artificial Analysis run)15.9%3.0%R1 0528
WeirdML41.6%9.0%R1 0528
ALE-Bench804.1Not measuredOnly R1 0528 measured
LMArena Text: coding14271260R1 0528
LMArena Text: software and IT14351260R1 0528
Neither model has a result on the other 32 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for R1 0528 and Llama 3.1 70B Instruct
BenchmarkR1 0528Llama 3.1 70B InstructLeader
AA Intelligence Index13.16.6R1 0528
Epoch Capabilities IndexNot measured125.9Only Llama 3.1 70B Instruct measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for R1 0528 and Llama 3.1 70B Instruct
BenchmarkR1 0528Llama 3.1 70B InstructLeader
τ²-Bench Telecom36.5%15.2%R1 0528
METR time horizons53.8%Not measuredOnly R1 0528 measured
BALROGNot measured27.9%Only Llama 3.1 70B Instruct measured
DeepResearch Bench35.1%Not measuredOnly R1 0528 measured
TheAgentCompanyNot measured6.9%Only Llama 3.1 70B Instruct measured
BrowseComp-Plus16.4%Not measuredOnly R1 0528 measured
Neither model has a result on the other 35 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
Reasoning benchmarks for R1 0528 and Llama 3.1 70B Instruct
BenchmarkR1 0528Llama 3.1 70B InstructLeader
GPQA Diamond (Artificial Analysis run)81.3%40.9%R1 0528
Humanity's Last Exam (Artificial Analysis run)15.8%4.5%R1 0528
GPQA Diamond (Epoch AI run)76.3%44.2%R1 0528
ARC-AGI21.2%Not measuredOnly R1 0528 measured
ARC-AGI-21.1%Not measuredOnly R1 0528 measured
SimpleBench40.8%Not measuredOnly R1 0528 measured
LMArena Text: hard prompts14151241R1 0528
LMArena Text: expert13941209R1 0528
LMArena Text: hard prompts in English14221261R1 0528
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for R1 0528 and Llama 3.1 70B Instruct
BenchmarkR1 0528Llama 3.1 70B InstructLeader
AA Math Index76.04.0R1 0528
AIME 2025 (Artificial Analysis run)76.0%4.0%R1 0528
OTIS Mock AIME66.4%3.6%R1 0528
MATH level 596.6%36.7%R1 0528
LMArena Text: math14001252R1 0528
LMArena Text: mathematical work14151253R1 0528
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for R1 0528 and Llama 3.1 70B Instruct
BenchmarkR1 0528Llama 3.1 70B InstructLeader
MMLU Pro (Artificial Analysis run)84.9%67.6%R1 0528
MMLUNot measured80.1%Only Llama 3.1 70B Instruct measured
LMArena Text: science14301276R1 0528
LMArena Text: medicine and healthcare14451257R1 0528
LMArena Text: legal and government14191283R1 0528
LMArena Text: business and finance14021235R1 0528
Neither model has a result on the other 12 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for R1 0528 and Llama 3.1 70B Instruct
BenchmarkR1 0528Llama 3.1 70B InstructLeader
Design Arena: websites1149Not measuredOnly R1 0528 measured
Design Arena: UI components1100Not measuredOnly R1 0528 measured
Design Arena: game dev1097Not measuredOnly R1 0528 measured
Design Arena: data viz1182Not measuredOnly R1 0528 measured
Design Arena: 3D1110Not measuredOnly R1 0528 measured
Design Arena: all code categories1138Not measuredOnly R1 0528 measured
Design Arena: SVG1038Not measuredOnly R1 0528 measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index170
General benchmarks for R1 0528 and Llama 3.1 70B Instruct
BenchmarkR1 0528Llama 3.1 70B InstructLeader
IFBench39.6%34.4%R1 0528
Long context reasoning (AA-LCR)55.7%Not measuredOnly R1 0528 measured
DTBenchNot measured60.0%Only Llama 3.1 70B Instruct measured
LMCANot measured14.8%Only Llama 3.1 70B Instruct measured
Fiction.LiveBench75.0%Not measuredOnly R1 0528 measured
Creative writing (Lech Mazur)81.9%Not measuredOnly R1 0528 measured
LMArena Text14281261R1 0528
LMArena Text: instruction following13821231R1 0528
LMArena Text: creative writing14051232R1 0528
LMArena Text: English14371294R1 0528
LMArena Text: non-English14121219R1 0528
LMArena Text: Chinese14421215R1 0528
LMArena Text: German14041222R1 0528
LMArena Text: Japanese13911132R1 0528
LMArena Text: Korean13601140R1 0528
LMArena Text: French14171262R1 0528
LMArena Text: Spanish14111253R1 0528
LMArena Text: Russian14231234R1 0528
LMArena Text: Polish1428Not measuredOnly R1 0528 measured
LMArena Text: multi-turn14051256R1 0528
LMArena Text: longer queries13911241R1 0528
LMArena Text: writing and language14021236R1 0528
LMArena Text: entertainment and media14001230R1 0528
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 R1 0528 and Llama 3.1 70B Instruct
BenchmarkR1 0528Llama 3.1 70B 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

R1 0528$0.0016Fits in one request
Llama 3.1 70B Instruct$0.0008Fits in one request

Llama 3.1 70B Instruct costs less

Repository review

50K input + 3K output tokens

R1 0528$0.032Fits in one request
Llama 3.1 70B Instruct$0.030Fits in one request

Llama 3.1 70B Instruct costs less

Agent loop

200K input + 10K output tokens

R1 0528$0.122Exceeds the context window
Llama 3.1 70B Instruct$0.118Exceeds the context window

Llama 3.1 70B 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 R1 0528 and Llama 3.1 70B Instruct
SpecificationDeepSeek R1 0528Meta Llama 3.1 70B Instruct
MakerDeepSeekMeta Llama
WeightsOpen weightsOpen weights
ReleasedMay 28, 2025July 23, 2024
Context window164K131K
Input $/Mtok$0.50$0.56
Output $/Mtok$2.18$0.56
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is R1 0528 better than Llama 3.1 70B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick R1 0528 for a larger context window (164K against 131K tokens).

Which is cheaper, R1 0528 or Llama 3.1 70B Instruct?

R1 0528 costs $0.50 per million input tokens and $2.18 per million output tokens; Llama 3.1 70B Instruct costs $0.56 and $0.56. Cost per solved task is known for neither of them.

Which has the bigger context window, R1 0528 or Llama 3.1 70B Instruct?

R1 0528, with 164K tokens against 131K.

How many benchmarks is the R1 0528 vs Llama 3.1 70B Instruct comparison based on?

41 benchmarks have a result for both models as of October 22, 2026. R1 0528's coding index rests on 0 independent benchmarks and Llama 3.1 70B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next