Enter opens the highlighted result. Esc closes.

GPT-4o (2024-08-06) vs Llama 3.3 70B Instruct

GPT-4o (2024-08-06) and Llama 3.3 70B Instruct tie on the Artificial Analysis Intelligence Index at 7.7, and Llama 3.3 70B Instruct costs 13.9x less per output token ($0.72 vs $10.00 per million). Updated October 22, 2026; 40 benchmarks have a result for both.

Replace GPT-4o (2024-08-06) Replace Llama 3.3 70B Instruct
GPT-4o (2024-08-06)OpenAI
Coding
No data
Overall
26.3
Output $/M
$10.00
27
Llama 3.3 70B InstructMeta Llama
Coding
No data
Overall
26.0
Output $/M
$0.72
12
vs boards won of 40 shared, 1 tied

GPT-4o (2024-08-06) or Llama 3.3 70B Instruct: which to pick

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

Pick GPT-4o (2024-08-06) for work measured by Humanity's Last Exam (Artificial Analysis run) or SimpleBench, where it leads.

Model AGPT-4o (2024-08-06)OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BLlama 3.3 70B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
40
GPT-4o (2024-08-06) only
18
Llama 3.3 70B Instruct only
12
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-4o (2024-08-06) not benchmarked, Llama 3.3 70B Instruct not benchmarked.
Widest category
General, 5.9 points apart on average over 18 shared benchmarks.
Widest single gap
Long context reasoning (AA-LCR): GPT-4o (2024-08-06) 41.0% against Llama 3.3 70B Instruct 15.7%, 25.3 points apart on a 0 to 100 scale.
Output price
GPT-4o (2024-08-06) $10.00 against Llama 3.3 70B Instruct $0.72 per million output tokens, 13.9x apart.
Context window
GPT-4o (2024-08-06) takes 128K tokens, Llama 3.3 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-4o (2024-08-06)BarsLlama 3.3 70B InstructTies
Coding40
Intelligence001 tie
Agentic work10
Reasoning52
Math40
Knowledge05
General135
All shared boards27121 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
Coding benchmarks for GPT-4o (2024-08-06) and Llama 3.3 70B Instruct
BenchmarkGPT-4o (2024-08-06)Llama 3.3 70B InstructLeader
Aider polyglot23.1%Not measuredOnly GPT-4o (2024-08-06) measured
SWE-bench Lite21.7%Not measuredOnly GPT-4o (2024-08-06) measured
AA Coding IndexNot measured11.9Only Llama 3.3 70B Instruct measured
LiveCodeBench (Artificial Analysis run)31.7%28.8%GPT-4o (2024-08-06)
Terminal-Bench Hard (Artificial Analysis run)8.3%3.0%GPT-4o (2024-08-06)
WeirdMLNot measured14.4%Only Llama 3.3 70B Instruct measured
LMArena Text: coding12831268GPT-4o (2024-08-06)
LMArena Text: software and IT12781273GPT-4o (2024-08-06)
Neither model has a result on the other 35 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index00
Intelligence benchmarks for GPT-4o (2024-08-06) and Llama 3.3 70B Instruct
BenchmarkGPT-4o (2024-08-06)Llama 3.3 70B InstructLeader
AA Intelligence Index7.77.7Tie
Epoch Capabilities IndexNot measured127.3Only Llama 3.3 70B Instruct measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-4o (2024-08-06) and Llama 3.3 70B Instruct
BenchmarkGPT-4o (2024-08-06)Llama 3.3 70B InstructLeader
τ²-Bench Telecom28.9%26.6%GPT-4o (2024-08-06)
BALROGNot measured23.0%Only Llama 3.3 70B Instruct measured
Berkeley Function Calling Leaderboard (BFCL)Not measured31.9%Only Llama 3.3 70B Instruct measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index52
Reasoning benchmarks for GPT-4o (2024-08-06) and Llama 3.3 70B Instruct
BenchmarkGPT-4o (2024-08-06)Llama 3.3 70B InstructLeader
MMMU Pro (Vals AI)64.0%Not measuredOnly GPT-4o (2024-08-06) measured
GPQA Diamond (Artificial Analysis run)52.1%49.8%GPT-4o (2024-08-06)
Humanity's Last Exam (Artificial Analysis run)2.3%3.6%Llama 3.3 70B Instruct
GPQA Diamond (Epoch AI run)49.2%47.4%GPT-4o (2024-08-06)
SimpleBench17.8%19.9%Llama 3.3 70B Instruct
Chess puzzles6.0%Not measuredOnly GPT-4o (2024-08-06) measured
LMArena Text: hard prompts12641257GPT-4o (2024-08-06)
LMArena Text: expert12411225GPT-4o (2024-08-06)
LMArena Text: hard prompts in English12771277GPT-4o (2024-08-06)
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for GPT-4o (2024-08-06) and Llama 3.3 70B Instruct
BenchmarkGPT-4o (2024-08-06)Llama 3.3 70B InstructLeader
AIME14.0%Not measuredOnly GPT-4o (2024-08-06) measured
MATH 500 (Vals AI)75.2%Not measuredOnly GPT-4o (2024-08-06) measured
MGSM (Vals AI)90.7%Not measuredOnly GPT-4o (2024-08-06) measured
AA Math IndexNot measured7.7Only Llama 3.3 70B Instruct measured
AIME 2025 (Artificial Analysis run)Not measured7.7%Only Llama 3.3 70B Instruct measured
OTIS Mock AIME6.4%5.1%GPT-4o (2024-08-06)
FrontierMath, tiers 1 to 30.4%Not measuredOnly GPT-4o (2024-08-06) measured
MATH level 553.3%41.6%GPT-4o (2024-08-06)
LMArena Text: math12851267GPT-4o (2024-08-06)
LMArena Text: mathematical work12831267GPT-4o (2024-08-06)
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for GPT-4o (2024-08-06) and Llama 3.3 70B Instruct
BenchmarkGPT-4o (2024-08-06)Llama 3.3 70B InstructLeader
MMLU Pro74.1%Not measuredOnly GPT-4o (2024-08-06) measured
LegalBench (Vals AI)80.1%Not measuredOnly GPT-4o (2024-08-06) measured
CorpFin (Vals AI)39.4%Not measuredOnly GPT-4o (2024-08-06) measured
TaxEval (Vals AI)71.1%Not measuredOnly GPT-4o (2024-08-06) measured
MortgageTax (Vals AI)61.0%Not measuredOnly GPT-4o (2024-08-06) measured
MedQA (Vals AI)88.2%Not measuredOnly GPT-4o (2024-08-06) measured
MMLU Pro (Artificial Analysis run)Not measured71.3%Only Llama 3.3 70B Instruct measured
SimpleQA Verified26.0%Not measuredOnly GPT-4o (2024-08-06) measured
MMLU84.3%86.3%Llama 3.3 70B Instruct
LMArena Text: science12741284Llama 3.3 70B Instruct
LMArena Text: medicine and healthcare12521275Llama 3.3 70B Instruct
LMArena Text: legal and government12751284Llama 3.3 70B Instruct
LMArena Text: business and finance12321243Llama 3.3 70B Instruct
Neither model has a result on the other 7 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for GPT-4o (2024-08-06) and Llama 3.3 70B Instruct
BenchmarkGPT-4o (2024-08-06)Llama 3.3 70B InstructLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index135
General benchmarks for GPT-4o (2024-08-06) and Llama 3.3 70B Instruct
BenchmarkGPT-4o (2024-08-06)Llama 3.3 70B InstructLeader
IFBench36.0%47.1%Llama 3.3 70B Instruct
Long context reasoning (AA-LCR)41.0%15.7%GPT-4o (2024-08-06)
DTBenchNot measured59.5%Only Llama 3.3 70B Instruct measured
LMCANot measured17.5%Only Llama 3.3 70B Instruct measured
Fiction.LiveBenchNot measured33.3%Only Llama 3.3 70B Instruct measured
LMArena Text12831274GPT-4o (2024-08-06)
LMArena Text: instruction following12671242GPT-4o (2024-08-06)
LMArena Text: creative writing12741250GPT-4o (2024-08-06)
LMArena Vision1065Not measuredOnly GPT-4o (2024-08-06) measured
LMArena Text: English12971303Llama 3.3 70B Instruct
LMArena Text: non-English12621236GPT-4o (2024-08-06)
LMArena Text: Chinese12541217GPT-4o (2024-08-06)
LMArena Text: German12571251GPT-4o (2024-08-06)
LMArena Text: Japanese12341150GPT-4o (2024-08-06)
LMArena Text: Korean12181142GPT-4o (2024-08-06)
LMArena Text: French12631282Llama 3.3 70B Instruct
LMArena Text: Spanish12691269Llama 3.3 70B Instruct
LMArena Text: Russian12721252GPT-4o (2024-08-06)
LMArena Text: PolishNot measured1259Only Llama 3.3 70B Instruct measured
LMArena Text: multi-turn12791280Llama 3.3 70B Instruct
LMArena Text: longer queries12831255GPT-4o (2024-08-06)
LMArena Text: writing and language12901255GPT-4o (2024-08-06)
LMArena Text: entertainment and media12671241GPT-4o (2024-08-06)
LMArena Vision: English1072Not measuredOnly GPT-4o (2024-08-06) measured
LMArena Vision: Chinese1009Not measuredOnly GPT-4o (2024-08-06) measured
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 GPT-4o (2024-08-06) and Llama 3.3 70B Instruct
BenchmarkGPT-4o (2024-08-06)Llama 3.3 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-4o (2024-08-06)$0.0075Fits in one request
Llama 3.3 70B Instruct$0.0008Fits in one request

Llama 3.3 70B Instruct costs less

Repository review

50K input + 3K output tokens

GPT-4o (2024-08-06)$0.155Fits in one request
Llama 3.3 70B Instruct$0.025Fits in one request

Llama 3.3 70B Instruct costs less

Agent loop

200K input + 10K output tokens

GPT-4o (2024-08-06)$0.600Exceeds the context window
Llama 3.3 70B Instruct$0.097Exceeds the context window

Llama 3.3 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 GPT-4o (2024-08-06) and Llama 3.3 70B Instruct
SpecificationOpenAI GPT-4o (2024-08-06)Meta Llama 3.3 70B Instruct
MakerOpenAIMeta Llama
WeightsNo public weights listedOpen weights
ReleasedAugust 6, 2024December 6, 2024
Context window128K131K
Input $/Mtok$2.50$0.45
Output $/Mtok$10.00$0.72
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4o (2024-08-06) better than Llama 3.3 70B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4o (2024-08-06) for work measured by Humanity's Last Exam (Artificial Analysis run) or SimpleBench, where it leads.

Which is cheaper, GPT-4o (2024-08-06) or Llama 3.3 70B Instruct?

GPT-4o (2024-08-06) costs $2.50 per million input tokens and $10.00 per million output tokens; Llama 3.3 70B Instruct costs $0.45 and $0.72. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-4o (2024-08-06) or Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct, with 131K tokens against 128K.

How many benchmarks is the GPT-4o (2024-08-06) vs Llama 3.3 70B Instruct comparison based on?

40 benchmarks have a result for both models as of October 22, 2026. GPT-4o (2024-08-06)'s coding index rests on 0 independent benchmarks and Llama 3.3 70B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next