Enter opens the highlighted result. Esc closes.

Gemma 2 27B vs Llama 3.3 70B Instruct

Gemma 2 27B and Llama 3.3 70B Instruct cost about the same per output token ($0.65 vs $0.72 per million). Updated October 21, 2026; 35 benchmarks have a result for both.

Replace Gemma 2 27B Replace Llama 3.3 70B Instruct
Gemma 2 27BGoogle
Coding
No data
Overall
No data
Output $/M
$0.65
4
Llama 3.3 70B InstructMeta Llama
Coding
No data
Overall
26.0
Output $/M
$0.72
31
vs boards won of 35 shared

Gemma 2 27B 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 Gemma 2 27B for output tokens 1.1x cheaper ($0.65 vs $0.72 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AGemma 2 27BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BLlama 3.3 70B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
35
Gemma 2 27B only
1
Llama 3.3 70B Instruct only
17
Like-for-like categories
6 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
Gemma 2 27B not benchmarked, Llama 3.3 70B Instruct not benchmarked.
Widest category
Reasoning, 10.4 points apart on average over 4 shared benchmarks.
Widest single gap
MATH level 5: Gemma 2 27B 27.9% against Llama 3.3 70B Instruct 41.6%, 13.7 points apart on a 0 to 100 scale.
Output price
Gemma 2 27B $0.65 against Llama 3.3 70B Instruct $0.72 per million output tokens, 1.1x apart.
Context window
Gemma 2 27B takes 8K 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
CategoryGemma 2 27BBarsLlama 3.3 70B InstructTies
Coding02
Intelligence01
Reasoning04
Math04
Knowledge05
General415
All shared boards431
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
Coding benchmarks for Gemma 2 27B and Llama 3.3 70B Instruct
BenchmarkGemma 2 27BLlama 3.3 70B InstructLeader
AA Coding IndexNot measured11.9Only Llama 3.3 70B Instruct measured
LiveCodeBench (Artificial Analysis run)Not measured28.8%Only Llama 3.3 70B Instruct measured
Terminal-Bench Hard (Artificial Analysis run)Not measured3.0%Only Llama 3.3 70B Instruct measured
WeirdMLNot measured14.4%Only Llama 3.3 70B Instruct measured
LMArena Text: coding12111268Llama 3.3 70B Instruct
LMArena Text: software and IT12281273Llama 3.3 70B Instruct
Neither model has a result on the other 33 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Gemma 2 27B and Llama 3.3 70B Instruct
BenchmarkGemma 2 27BLlama 3.3 70B InstructLeader
AA Intelligence IndexNot measured7.7Only Llama 3.3 70B Instruct measured
Epoch Capabilities Index122.1127.3Llama 3.3 70B Instruct
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Agentic work benchmarks for Gemma 2 27B and Llama 3.3 70B Instruct
BenchmarkGemma 2 27BLlama 3.3 70B InstructLeader
τ²-Bench TelecomNot measured26.6%Only Llama 3.3 70B Instruct measured
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 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for Gemma 2 27B and Llama 3.3 70B Instruct
BenchmarkGemma 2 27BLlama 3.3 70B InstructLeader
GPQA Diamond (Artificial Analysis run)Not measured49.8%Only Llama 3.3 70B Instruct measured
Humanity's Last Exam (Artificial Analysis run)Not measured3.6%Only Llama 3.3 70B Instruct measured
GPQA Diamond (Epoch AI run)36.5%47.4%Llama 3.3 70B Instruct
SimpleBenchNot measured19.9%Only Llama 3.3 70B Instruct measured
LMArena Text: hard prompts11981257Llama 3.3 70B Instruct
LMArena Text: expert11711225Llama 3.3 70B Instruct
LMArena Text: hard prompts in English12061277Llama 3.3 70B Instruct
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for Gemma 2 27B and Llama 3.3 70B Instruct
BenchmarkGemma 2 27BLlama 3.3 70B InstructLeader
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 AIME1.4%5.1%Llama 3.3 70B Instruct
MATH level 527.9%41.6%Llama 3.3 70B Instruct
LMArena Text: math12121267Llama 3.3 70B Instruct
LMArena Text: mathematical work12211267Llama 3.3 70B Instruct
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 Gemma 2 27B and Llama 3.3 70B Instruct
BenchmarkGemma 2 27BLlama 3.3 70B InstructLeader
LegalBench (Vals AI)68.0%Not measuredOnly Gemma 2 27B measured
MMLU Pro (Artificial Analysis run)Not measured71.3%Only Llama 3.3 70B Instruct measured
MMLU75.7%86.3%Llama 3.3 70B Instruct
LMArena Text: science12281284Llama 3.3 70B Instruct
LMArena Text: medicine and healthcare11981275Llama 3.3 70B Instruct
LMArena Text: legal and government12411284Llama 3.3 70B Instruct
LMArena Text: business and finance12081243Llama 3.3 70B Instruct
Neither model has a result on the other 11 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Gemma 2 27B and Llama 3.3 70B Instruct
BenchmarkGemma 2 27BLlama 3.3 70B InstructLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index415
General benchmarks for Gemma 2 27B and Llama 3.3 70B Instruct
BenchmarkGemma 2 27BLlama 3.3 70B InstructLeader
IFBenchNot measured47.1%Only Llama 3.3 70B Instruct measured
Long context reasoning (AA-LCR)Not measured15.7%Only Llama 3.3 70B Instruct measured
DTBench48.0%59.5%Llama 3.3 70B Instruct
LMCA7.1%17.5%Llama 3.3 70B Instruct
Fiction.LiveBenchNot measured33.3%Only Llama 3.3 70B Instruct measured
LMArena Text12311274Llama 3.3 70B Instruct
LMArena Text: instruction following12061242Llama 3.3 70B Instruct
LMArena Text: creative writing12401250Llama 3.3 70B Instruct
LMArena Text: English12421303Llama 3.3 70B Instruct
LMArena Text: non-English12171236Llama 3.3 70B Instruct
LMArena Text: Chinese12211217Gemma 2 27B
LMArena Text: German12091251Llama 3.3 70B Instruct
LMArena Text: Japanese11751150Gemma 2 27B
LMArena Text: Korean11741142Gemma 2 27B
LMArena Text: French12481282Llama 3.3 70B Instruct
LMArena Text: Spanish12281269Llama 3.3 70B Instruct
LMArena Text: Russian12341252Llama 3.3 70B Instruct
LMArena Text: Polish12771259Gemma 2 27B
LMArena Text: multi-turn12241280Llama 3.3 70B Instruct
LMArena Text: longer queries12301255Llama 3.3 70B Instruct
LMArena Text: writing and language12491255Llama 3.3 70B Instruct
LMArena Text: entertainment and media12121241Llama 3.3 70B Instruct
Neither model has a result on the other 24 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemma 2 27B and Llama 3.3 70B Instruct
BenchmarkGemma 2 27BLlama 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

Gemma 2 27B$0.0010Fits 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

Gemma 2 27B$0.034Exceeds the context window
Llama 3.3 70B Instruct$0.025Fits in one request

Llama 3.3 70B Instruct costs less

Agent loop

200K input + 10K output tokens

Gemma 2 27B$0.137Exceeds 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 Gemma 2 27B and Llama 3.3 70B Instruct
SpecificationGoogle Gemma 2 27BMeta Llama 3.3 70B Instruct
MakerGoogleMeta Llama
WeightsOpen weightsOpen weights
ReleasedJuly 13, 2024December 6, 2024
Context window8K131K
Input $/Mtok$0.65$0.45
Output $/Mtok$0.65$0.72
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 2 27B 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 Gemma 2 27B for output tokens 1.1x cheaper ($0.65 vs $0.72 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Gemma 2 27B or Llama 3.3 70B Instruct?

Gemma 2 27B costs $0.65 per million input tokens and $0.65 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, Gemma 2 27B or Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct, with 131K tokens against 8K.

How many benchmarks is the Gemma 2 27B vs Llama 3.3 70B Instruct comparison based on?

35 benchmarks have a result for both models as of October 21, 2026. Gemma 2 27B'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