Enter opens the highlighted result. Esc closes.

Llama 3.1 70B Instruct vs Mistral Medium 3

Mistral Medium 3 leads Llama 3.1 70B Instruct on the Artificial Analysis Intelligence Index, 9.0 to 6.6, and Llama 3.1 70B Instruct costs 3.6x less per output token ($0.56 vs $2.00 per million). Updated October 22, 2026; 39 benchmarks have a result for both.

Replace Llama 3.1 70B Instruct Replace Mistral Medium 3
Llama 3.1 70B InstructMeta Llama
Coding
No data
Overall
24.3
Output $/M
$0.56
1
Mistral Medium 3Mistral AI
Coding
No data
Overall
No data
Output $/M
$2.00
38
vs boards won of 39 shared

Llama 3.1 70B Instruct or Mistral Medium 3: 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 3.6x cheaper ($0.56 vs $2.00 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model ALlama 3.1 70B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved taskModel BMistral Medium 3Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
39
Llama 3.1 70B Instruct only
8
Mistral Medium 3 only
18
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, Mistral Medium 3 not benchmarked.
Widest category
Math, 21.6 points apart on average over 4 shared benchmarks.
Widest single gap
LMArena Text: Japanese: Llama 3.1 70B Instruct 1132 against Mistral Medium 3 1316, 30.6 points apart on a 0 to 100 scale.
Output price
Llama 3.1 70B Instruct $0.56 against Mistral Medium 3 $2.00 per million output tokens, 3.6x 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 InstructBarsMistral Medium 3Ties
Coding04
Intelligence02
Agentic work01
Reasoning14
Math04
Knowledge05
General018
All shared boards138
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Llama 3.1 70B Instruct and Mistral Medium 3
BenchmarkLlama 3.1 70B InstructMistral Medium 3Leader
LiveCodeBench (Artificial Analysis run)23.2%40.0%Mistral Medium 3
Terminal-Bench Hard (Artificial Analysis run)3.0%3.8%Mistral Medium 3
WeirdML9.0%Not measuredOnly Llama 3.1 70B Instruct measured
LMArena Text: coding12601385Mistral Medium 3
LMArena Text: software and IT12601385Mistral Medium 3
Neither model has a result on the other 34 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Llama 3.1 70B Instruct and Mistral Medium 3
BenchmarkLlama 3.1 70B InstructMistral Medium 3Leader
AA Intelligence Index6.69.0Mistral Medium 3
Epoch Capabilities Index125.9134.0Mistral Medium 3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Llama 3.1 70B Instruct and Mistral Medium 3
BenchmarkLlama 3.1 70B InstructMistral Medium 3Leader
τ²-Bench Telecom15.2%24.3%Mistral Medium 3
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 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index14
Reasoning benchmarks for Llama 3.1 70B Instruct and Mistral Medium 3
BenchmarkLlama 3.1 70B InstructMistral Medium 3Leader
GPQA Diamond (Artificial Analysis run)40.9%57.8%Mistral Medium 3
Humanity's Last Exam (Artificial Analysis run)4.5%4.1%Llama 3.1 70B Instruct
GPQA Diamond (Epoch AI run)44.2%Not measuredOnly Llama 3.1 70B Instruct measured
LMArena Text: hard prompts12411364Mistral Medium 3
LMArena Text: expert12091342Mistral Medium 3
LMArena Text: hard prompts in English12611374Mistral Medium 3
LMArena Vision: diagramsNot measured1155Only Mistral Medium 3 measured
LMArena Vision: homeworkNot measured1165Only Mistral Medium 3 measured
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for Llama 3.1 70B Instruct and Mistral Medium 3
BenchmarkLlama 3.1 70B InstructMistral Medium 3Leader
AA Math Index4.030.3Mistral Medium 3
AIME 2025 (Artificial Analysis run)4.0%30.3%Mistral Medium 3
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: math12521353Mistral Medium 3
LMArena Text: mathematical work12531354Mistral Medium 3
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 3.1 70B Instruct and Mistral Medium 3
BenchmarkLlama 3.1 70B InstructMistral Medium 3Leader
MMLU Pro (Artificial Analysis run)67.6%76.0%Mistral Medium 3
MMLU80.1%Not measuredOnly Llama 3.1 70B Instruct measured
LMArena Text: science12761381Mistral Medium 3
LMArena Text: medicine and healthcare12571381Mistral Medium 3
LMArena Text: legal and government12831384Mistral Medium 3
LMArena Text: business and finance12351352Mistral Medium 3
Neither model has a result on the other 12 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Web design benchmarks for Llama 3.1 70B Instruct and Mistral Medium 3
BenchmarkLlama 3.1 70B InstructMistral Medium 3Leader
Design Arena: websitesNot measured1079Only Mistral Medium 3 measured
Design Arena: UI componentsNot measured1022Only Mistral Medium 3 measured
Design Arena: game devNot measured1017Only Mistral Medium 3 measured
Design Arena: data vizNot measured1034Only Mistral Medium 3 measured
Design Arena: 3DNot measured1083Only Mistral Medium 3 measured
Design Arena: all code categoriesNot measured1068Only Mistral Medium 3 measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index018
General benchmarks for Llama 3.1 70B Instruct and Mistral Medium 3
BenchmarkLlama 3.1 70B InstructMistral Medium 3Leader
IFBench34.4%39.3%Mistral Medium 3
Long context reasoning (AA-LCR)Not measured31.3%Only Mistral Medium 3 measured
DTBench60.0%62.3%Mistral Medium 3
LMCA14.8%Not measuredOnly Llama 3.1 70B Instruct measured
LMArena Text12611370Mistral Medium 3
LMArena Text: instruction following12311338Mistral Medium 3
LMArena Text: creative writing12321343Mistral Medium 3
LMArena VisionNot measured1157Only Mistral Medium 3 measured
LMArena Text: English12941385Mistral Medium 3
LMArena Text: non-English12191353Mistral Medium 3
LMArena Text: Chinese12151374Mistral Medium 3
LMArena Text: German12221377Mistral Medium 3
LMArena Text: Japanese11321316Mistral Medium 3
LMArena Text: Korean11401304Mistral Medium 3
LMArena Text: French12621368Mistral Medium 3
LMArena Text: Spanish12531364Mistral Medium 3
LMArena Text: Russian12341359Mistral Medium 3
LMArena Text: PolishNot measured1371Only Mistral Medium 3 measured
LMArena Text: multi-turn12561384Mistral Medium 3
LMArena Text: longer queries12411360Mistral Medium 3
LMArena Text: writing and language12361352Mistral Medium 3
LMArena Text: entertainment and media12301335Mistral Medium 3
LMArena Vision: EnglishNot measured1172Only Mistral Medium 3 measured
LMArena Vision: ChineseNot measured1161Only Mistral Medium 3 measured
LMArena Vision: reading textNot measured1154Only Mistral Medium 3 measured
LMArena Vision: humorNot measured1145Only Mistral Medium 3 measured
LMArena Vision: captioningNot measured1094Only Mistral Medium 3 measured
LMArena Vision: recognizing thingsNot measured1141Only Mistral Medium 3 measured
LMArena Vision: creative writingNot measured1146Only Mistral Medium 3 measured
Neither model has a result on the other 17 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 Mistral Medium 3
BenchmarkLlama 3.1 70B InstructMistral Medium 3Leader
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
Mistral Medium 3$0.0014Fits in one request

Llama 3.1 70B Instruct costs less

Repository review

50K input + 3K output tokens

Llama 3.1 70B Instruct$0.030Fits in one request
Mistral Medium 3$0.026Fits in one request

Mistral Medium 3 costs less

Agent loop

200K input + 10K output tokens

Llama 3.1 70B Instruct$0.118Exceeds the context window
Mistral Medium 3$0.100Exceeds the context window

Mistral Medium 3 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 Mistral Medium 3
SpecificationMeta Llama 3.1 70B InstructMistral Medium 3
MakerMeta LlamaMistral AI
WeightsOpen weightsNo public weights listed
ReleasedJuly 23, 2024May 7, 2025
Context window131K131K
Input $/Mtok$0.56$0.40
Output $/Mtok$0.56$2.00
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 Mistral Medium 3 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 3.6x cheaper ($0.56 vs $2.00 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, Llama 3.1 70B Instruct or Mistral Medium 3?

Llama 3.1 70B Instruct costs $0.56 per million input tokens and $0.56 per million output tokens; Mistral Medium 3 costs $0.40 and $2.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Llama 3.1 70B Instruct or Mistral Medium 3?

Neither: both take 131K tokens.

How many benchmarks is the Llama 3.1 70B Instruct vs Mistral Medium 3 comparison based on?

39 benchmarks have a result for both models as of October 22, 2026. Llama 3.1 70B Instruct's coding index rests on 0 independent benchmarks and Mistral Medium 3's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next