Enter opens the highlighted result. Esc closes.

Llama 3.1 8B Instruct vs Mistral Small 3

Llama 3.1 8B Instruct leads Mistral Small 3 on the Artificial Analysis Intelligence Index, 6.9 to 6.7, at about the same output price ($0.08 vs $0.08 per million). Updated October 22, 2026; 36 benchmarks have a result for both.

Replace Llama 3.1 8B Instruct Replace Mistral Small 3
Llama 3.1 8B InstructMeta Llama
Coding
No data
Overall
17.9
Output $/M
$0.08
4
Mistral Small 3Mistral AI
Coding
No data
Overall
No data
Output $/M
$0.08
30
vs boards won of 36 shared, 2 tied

Llama 3.1 8B Instruct or Mistral Small 3: which to pick

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

Pick Llama 3.1 8B Instruct for a larger context window (131K against 33K tokens) and work measured by LiveCodeBench (Artificial Analysis run) or LMArena Text: coding, where it leads.

Model ALlama 3.1 8B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved taskModel BMistral Small 3Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
36
Llama 3.1 8B Instruct only
15
Mistral Small 3 only
0
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 8B Instruct not benchmarked, Mistral Small 3 not benchmarked.
Widest category
Coding, 10.3 points apart on average over 3 shared benchmarks.
Widest single gap
LMArena Text: Korean: Llama 3.1 8B Instruct 1053 against Mistral Small 3 1188, 22.6 points apart on a 0 to 100 scale.
Output price
Both cost $0.08 per million output tokens.
Context window
Llama 3.1 8B Instruct takes 131K tokens, Mistral Small 3 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 3.1 8B InstructBarsMistral Small 3Ties
Coding03
Intelligence10
Agentic work01
Reasoning14
Math022 ties
Knowledge05
General215
All shared boards4302 ties
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for Llama 3.1 8B Instruct and Mistral Small 3
BenchmarkLlama 3.1 8B InstructMistral Small 3Leader
AA Coding Index5.4Not measuredOnly Llama 3.1 8B Instruct measured
LiveCodeBench (Artificial Analysis run)11.6%25.2%Mistral Small 3
Terminal-Bench Hard (Artificial Analysis run)0.8%Not measuredOnly Llama 3.1 8B Instruct measured
WeirdML1.7%Not measuredOnly Llama 3.1 8B Instruct measured
LMArena Text: coding11951246Mistral Small 3
LMArena Text: software and IT11951248Mistral Small 3
Neither model has a result on the other 33 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Llama 3.1 8B Instruct and Mistral Small 3
BenchmarkLlama 3.1 8B InstructMistral Small 3Leader
AA Intelligence Index6.96.7Llama 3.1 8B Instruct
Epoch Capabilities Index116.5Not measuredOnly Llama 3.1 8B Instruct measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Llama 3.1 8B Instruct and Mistral Small 3
BenchmarkLlama 3.1 8B InstructMistral Small 3Leader
τ²-Bench Telecom16.4%19.6%Mistral Small 3
BALROG15.1%Not measuredOnly Llama 3.1 8B Instruct measured
Berkeley Function Calling Leaderboard (BFCL)25.8%Not measuredOnly Llama 3.1 8B 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 8B Instruct and Mistral Small 3
BenchmarkLlama 3.1 8B InstructMistral Small 3Leader
GPQA Diamond (Artificial Analysis run)25.9%46.2%Mistral Small 3
Humanity's Last Exam (Artificial Analysis run)5.3%3.8%Llama 3.1 8B Instruct
GPQA Diamond (Epoch AI run)27.0%Not measuredOnly Llama 3.1 8B Instruct measured
LMArena Text: hard prompts11751233Mistral Small 3
LMArena Text: expert11441202Mistral Small 3
LMArena Text: hard prompts in English11961243Mistral Small 3
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 8B Instruct and Mistral Small 3
BenchmarkLlama 3.1 8B InstructMistral Small 3Leader
AA Math Index4.34.3Tie
AIME 2025 (Artificial Analysis run)4.3%4.3%Tie
OTIS Mock AIME1.7%Not measuredOnly Llama 3.1 8B Instruct measured
MATH level 522.9%Not measuredOnly Llama 3.1 8B Instruct measured
GSM8K82.4%Not measuredOnly Llama 3.1 8B Instruct measured
LMArena Text: math11791240Mistral Small 3
LMArena Text: mathematical work11801243Mistral Small 3
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for Llama 3.1 8B Instruct and Mistral Small 3
BenchmarkLlama 3.1 8B InstructMistral Small 3Leader
MMLU Pro (Artificial Analysis run)47.6%65.2%Mistral Small 3
MMLU56.1%Not measuredOnly Llama 3.1 8B Instruct measured
LMArena Text: science11931235Mistral Small 3
LMArena Text: medicine and healthcare11821215Mistral Small 3
LMArena Text: legal and government12061219Mistral Small 3
LMArena Text: business and finance11661205Mistral Small 3
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 8B Instruct and Mistral Small 3
BenchmarkLlama 3.1 8B InstructMistral Small 3Leader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index215
General benchmarks for Llama 3.1 8B Instruct and Mistral Small 3
BenchmarkLlama 3.1 8B InstructMistral Small 3Leader
IFBench28.6%26.4%Llama 3.1 8B Instruct
Long context reasoning (AA-LCR)18.0%0.0%Llama 3.1 8B Instruct
DTBench50.9%Not measuredOnly Llama 3.1 8B Instruct measured
LMCA5.4%Not measuredOnly Llama 3.1 8B Instruct measured
PIQA81.2%Not measuredOnly Llama 3.1 8B Instruct measured
LMArena Text11871234Mistral Small 3
LMArena Text: instruction following11591214Mistral Small 3
LMArena Text: creative writing11541194Mistral Small 3
LMArena Text: English12181256Mistral Small 3
LMArena Text: non-English11481198Mistral Small 3
LMArena Text: Chinese11511204Mistral Small 3
LMArena Text: German11441211Mistral Small 3
LMArena Text: Japanese10611111Mistral Small 3
LMArena Text: Korean10531188Mistral Small 3
LMArena Text: French11781204Mistral Small 3
LMArena Text: Spanish1169Not measuredOnly Llama 3.1 8B Instruct measured
LMArena Text: Russian11581216Mistral Small 3
LMArena Text: multi-turn11721217Mistral Small 3
LMArena Text: longer queries11811246Mistral Small 3
LMArena Text: writing and language11621214Mistral Small 3
LMArena Text: entertainment and media11451184Mistral Small 3
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 8B Instruct and Mistral Small 3
BenchmarkLlama 3.1 8B InstructMistral Small 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 8B Instruct$0.0001Fits in one request
Mistral Small 3$0.0001Fits in one request

Same cost

Repository review

50K input + 3K output tokens

Llama 3.1 8B Instruct$0.0027Fits in one request
Mistral Small 3$0.0027Exceeds the context window

Same cost

Agent loop

200K input + 10K output tokens

Llama 3.1 8B Instruct$0.011Exceeds the context window
Mistral Small 3$0.011Exceeds the context window

Same cost

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 8B Instruct and Mistral Small 3
SpecificationMeta Llama 3.1 8B InstructMistral Small 3
MakerMeta LlamaMistral AI
WeightsOpen weightsOpen weights
ReleasedJuly 23, 2024January 30, 2025
Context window131K33K
Input $/Mtok$0.05$0.05
Output $/Mtok$0.08$0.08
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Llama 3.1 8B Instruct better than Mistral Small 3 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Llama 3.1 8B Instruct for a larger context window (131K against 33K tokens) and work measured by LiveCodeBench (Artificial Analysis run) or LMArena Text: coding, where it leads.

Which is cheaper, Llama 3.1 8B Instruct or Mistral Small 3?

Llama 3.1 8B Instruct costs $0.05 per million input tokens and $0.08 per million output tokens; Mistral Small 3 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 8B Instruct or Mistral Small 3?

Llama 3.1 8B Instruct, with 131K tokens against 33K.

How many benchmarks is the Llama 3.1 8B Instruct vs Mistral Small 3 comparison based on?

36 benchmarks have a result for both models as of October 22, 2026. Llama 3.1 8B Instruct's coding index rests on 0 independent benchmarks and Mistral Small 3's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next