Enter opens the highlighted result. Esc closes.

GPT-5 Mini vs Llama 3.1 70B Instruct

GPT-5 Mini leads Llama 3.1 70B Instruct on the Artificial Analysis Intelligence Index, 20.6 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 21, 2026; 44 benchmarks have a result for both.

Replace GPT-5 Mini Replace Llama 3.1 70B Instruct
GPT-5 MiniOpenAI
Coding
34.2
Overall
20.6
Output $/M
$2.00
44
Llama 3.1 70B InstructMeta Llama
Coding
No data
Overall
6.6
Output $/M
$0.56
0
vs boards won of 44 shared

GPT-5 Mini or Llama 3.1 70B Instruct: which to pick

Only GPT-5 Mini has a coding score, 34.2 on the Vibe Coding Index; Llama 3.1 70B Instruct has none, 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).

Model AGPT-5 MiniOpenAI34.2/1002 independent benchmarks$0.08 per solved taskModel BLlama 3.1 70B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
44
GPT-5 Mini only
54
Llama 3.1 70B Instruct only
3
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
GPT-5 Mini 34.2 from 2 benchmarks, Llama 3.1 70B Instruct not benchmarked.
Widest category
Math, 59.9 points apart on average over 6 shared benchmarks.
Widest single gap
AA Math Index: GPT-5 Mini 90.7 against Llama 3.1 70B Instruct 4.0, 86.7 points apart on a 0 to 100 scale.
Output price
GPT-5 Mini $2.00 against Llama 3.1 70B Instruct $0.56 per million output tokens, 3.6x apart.
Context window
GPT-5 Mini takes 400K 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
CategoryGPT-5 MiniBarsLlama 3.1 70B InstructTies
Coding50
Intelligence20
Agentic work10
Reasoning60
Math60
Knowledge50
General190
All shared boards440
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
Coding benchmarks for GPT-5 Mini and Llama 3.1 70B Instruct
BenchmarkGPT-5 MiniLlama 3.1 70B InstructLeader
SWE-bench Verified59.8%Not measuredOnly GPT-5 Mini measured
SWE-bench Multilingual39.7%Not measuredOnly GPT-5 Mini measured
LiveCodeBench (Vals AI)86.6%Not measuredOnly GPT-5 Mini measured
SWE-bench Verified (Vals AI)60.8%Not measuredOnly GPT-5 Mini measured
Vibe Code Bench (Vals AI)14.2%Not measuredOnly GPT-5 Mini measured
LiveCodeBench (Artificial Analysis run)83.8%23.2%GPT-5 Mini
SciCode39.0%Not measuredOnly GPT-5 Mini measured
Terminal-Bench Hard (Artificial Analysis run)33.3%3.0%GPT-5 Mini
Terminal-Bench34.8%Not measuredOnly GPT-5 Mini measured
WeirdML52.7%9.0%GPT-5 Mini
LMArena Text: coding14061260GPT-5 Mini
LMArena Text: software and IT13941260GPT-5 Mini
Neither model has a result on the other 26 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5 Mini and Llama 3.1 70B Instruct
BenchmarkGPT-5 MiniLlama 3.1 70B InstructLeader
AA Intelligence Index20.66.6GPT-5 Mini
Epoch Capabilities Index145.3125.9GPT-5 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-5 Mini and Llama 3.1 70B Instruct
BenchmarkGPT-5 MiniLlama 3.1 70B InstructLeader
τ²-Bench Telecom71.1%15.2%GPT-5 Mini
BALROGNot measured27.9%Only Llama 3.1 70B Instruct measured
TheAgentCompanyNot measured6.9%Only Llama 3.1 70B Instruct measured
Vending-Bench 2-$31Not measuredOnly GPT-5 Mini 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 GPT-5 Mini and Llama 3.1 70B Instruct
BenchmarkGPT-5 MiniLlama 3.1 70B InstructLeader
GPQA Diamond80.3%Not measuredOnly GPT-5 Mini measured
MMMU Pro (Vals AI)78.9%Not measuredOnly GPT-5 Mini measured
GPQA Diamond (Artificial Analysis run)82.8%40.9%GPT-5 Mini
Humanity's Last Exam (Artificial Analysis run)21.5%4.5%GPT-5 Mini
GPQA Diamond (Epoch AI run)75.0%44.2%GPT-5 Mini
ARC-AGI54.3%Not measuredOnly GPT-5 Mini measured
ARC-AGI-24.4%Not measuredOnly GPT-5 Mini measured
Chess puzzles24.0%Not measuredOnly GPT-5 Mini measured
Mystery game puzzles10.0%Not measuredOnly GPT-5 Mini measured
VPCT40.2%Not measuredOnly GPT-5 Mini measured
LMArena Text: hard prompts13801241GPT-5 Mini
LMArena Text: expert13791209GPT-5 Mini
LMArena Text: hard prompts in English13831261GPT-5 Mini
LMArena Vision: diagrams1202Not measuredOnly GPT-5 Mini measured
LMArena Vision: homework1210Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for GPT-5 Mini and Llama 3.1 70B Instruct
BenchmarkGPT-5 MiniLlama 3.1 70B InstructLeader
AIME91.5%Not measuredOnly GPT-5 Mini measured
MATH 500 (Vals AI)94.8%Not measuredOnly GPT-5 Mini measured
MGSM (Vals AI)92.6%Not measuredOnly GPT-5 Mini measured
AA Math Index90.74.0GPT-5 Mini
AIME 2025 (Artificial Analysis run)90.7%4.0%GPT-5 Mini
OTIS Mock AIME86.7%3.6%GPT-5 Mini
FrontierMath, tiers 1 to 346.7%Not measuredOnly GPT-5 Mini measured
FrontierMath, tier 412.2%Not measuredOnly GPT-5 Mini measured
ProofBench9.0%Not measuredOnly GPT-5 Mini measured
MATH level 597.8%36.7%GPT-5 Mini
LMArena Text: math13781252GPT-5 Mini
LMArena Text: mathematical work13801253GPT-5 Mini
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for GPT-5 Mini and Llama 3.1 70B Instruct
BenchmarkGPT-5 MiniLlama 3.1 70B InstructLeader
MMLU Pro82.2%Not measuredOnly GPT-5 Mini measured
LegalBench (Vals AI)81.8%Not measuredOnly GPT-5 Mini measured
CaseLaw (Vals AI)68.5%Not measuredOnly GPT-5 Mini measured
CorpFin (Vals AI)60.2%Not measuredOnly GPT-5 Mini measured
TaxEval (Vals AI)75.2%Not measuredOnly GPT-5 Mini measured
MortgageTax (Vals AI)66.9%Not measuredOnly GPT-5 Mini measured
MedQA (Vals AI)96.1%Not measuredOnly GPT-5 Mini measured
MedCode (Vals AI)43.0%Not measuredOnly GPT-5 Mini measured
MMLU Pro (Artificial Analysis run)83.7%67.6%GPT-5 Mini
SimpleQA Verified21.6%Not measuredOnly GPT-5 Mini measured
MMLUNot measured80.1%Only Llama 3.1 70B Instruct measured
LMArena Text: science13711276GPT-5 Mini
LMArena Text: medicine and healthcare13801257GPT-5 Mini
LMArena Text: legal and government13751283GPT-5 Mini
LMArena Text: business and finance13581235GPT-5 Mini
Neither model has a result on the other 2 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GPT-5 Mini and Llama 3.1 70B Instruct
BenchmarkGPT-5 MiniLlama 3.1 70B InstructLeader
Design Arena: websites1125Not measuredOnly GPT-5 Mini measured
Design Arena: UI components1106Not measuredOnly GPT-5 Mini measured
Design Arena: game dev1130Not measuredOnly GPT-5 Mini measured
Design Arena: data viz1130Not measuredOnly GPT-5 Mini measured
Design Arena: 3D1037Not measuredOnly GPT-5 Mini measured
Design Arena: all code categories1115Not measuredOnly GPT-5 Mini measured
Design Arena: SVG1091Not measuredOnly GPT-5 Mini measured
Design Arena: ASCII art1125Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index190
General benchmarks for GPT-5 Mini and Llama 3.1 70B Instruct
BenchmarkGPT-5 MiniLlama 3.1 70B InstructLeader
SAGE (Vals AI)43.0%Not measuredOnly GPT-5 Mini measured
MedScribe (Vals AI)80.6%Not measuredOnly GPT-5 Mini measured
IFBench75.4%34.4%GPT-5 Mini
Long context reasoning (AA-LCR)72.3%Not measuredOnly GPT-5 Mini measured
DTBench80.5%60.0%GPT-5 Mini
LMCA34.2%14.8%GPT-5 Mini
Fiction.LiveBench69.4%Not measuredOnly GPT-5 Mini measured
Creative writing (Lech Mazur)83.1%Not measuredOnly GPT-5 Mini measured
LMArena Text13731261GPT-5 Mini
LMArena Text: instruction following13571231GPT-5 Mini
LMArena Text: creative writing13251232GPT-5 Mini
LMArena Vision1202Not measuredOnly GPT-5 Mini measured
LMArena Text: English13791294GPT-5 Mini
LMArena Text: non-English13631219GPT-5 Mini
LMArena Text: Chinese13861215GPT-5 Mini
LMArena Text: German13661222GPT-5 Mini
LMArena Text: Japanese13411132GPT-5 Mini
LMArena Text: Korean13081140GPT-5 Mini
LMArena Text: French13861262GPT-5 Mini
LMArena Text: Spanish13541253GPT-5 Mini
LMArena Text: Russian13621234GPT-5 Mini
LMArena Text: Polish1378Not measuredOnly GPT-5 Mini measured
LMArena Text: multi-turn13631256GPT-5 Mini
LMArena Text: longer queries13551241GPT-5 Mini
LMArena Text: writing and language13441236GPT-5 Mini
LMArena Text: entertainment and media13401230GPT-5 Mini
LMArena Vision: English1216Not measuredOnly GPT-5 Mini measured
LMArena Vision: Chinese1214Not measuredOnly GPT-5 Mini measured
LMArena Vision: reading text1199Not measuredOnly GPT-5 Mini measured
LMArena Vision: humor1205Not measuredOnly GPT-5 Mini measured
LMArena Vision: captioning1217Not measuredOnly GPT-5 Mini measured
LMArena Vision: recognizing things1226Not measuredOnly GPT-5 Mini measured
LMArena Vision: creative writing1181Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5 Mini and Llama 3.1 70B Instruct
BenchmarkGPT-5 MiniLlama 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

GPT-5 Mini$0.0013Fits 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

GPT-5 Mini$0.018Fits in one request
Llama 3.1 70B Instruct$0.030Fits in one request

GPT-5 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-5 Mini$0.070Fits in one request
Llama 3.1 70B Instruct$0.118Exceeds the context window

GPT-5 Mini 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 GPT-5 Mini and Llama 3.1 70B Instruct
SpecificationOpenAI GPT-5 MiniMeta Llama 3.1 70B Instruct
MakerOpenAIMeta Llama
WeightsNo public weights listedOpen weights
ReleasedAugust 7, 2025July 23, 2024
Context window400K131K
Input $/Mtok$0.25$0.56
Output $/Mtok$2.00$0.56
Coding index34.2Not benchmarked
Independent measurements behind it20
Cost per solved task$0.08Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5 Mini better than Llama 3.1 70B Instruct for coding?

Only GPT-5 Mini has a coding score, 34.2 on the Vibe Coding Index; Llama 3.1 70B Instruct has none, 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).

Which is cheaper, GPT-5 Mini or Llama 3.1 70B Instruct?

GPT-5 Mini costs $0.25 per million input tokens and $2.00 per million output tokens; Llama 3.1 70B Instruct costs $0.56 and $0.56. Cost per solved task is known for GPT-5 Mini only.

Which has the bigger context window, GPT-5 Mini or Llama 3.1 70B Instruct?

GPT-5 Mini, with 400K tokens against 131K.

How many benchmarks is the GPT-5 Mini vs Llama 3.1 70B Instruct comparison based on?

44 benchmarks have a result for both models as of October 21, 2026. GPT-5 Mini's coding index rests on 2 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