Compare · ModelsLive · 2 picked · head to head

Gemma 2 27B vs Llama 3.1 70B Instruct

Side by side · benchmarks, pricing, and signals you can act on.

CiteAdd another

Winner summary

Llama 3.1 70B Instruct wins on 12/13 benchmarks

Llama 3.1 70B Instruct wins 12 of 13 shared benchmarks. Leads in arena · general · knowledge.

Gemma 2 27B

1 / 13

Llama 3.1 70B Instruct

12 / 13

Category leads

arena·Llama 3.1 70B Instructgeneral·Llama 3.1 70B Instructknowledge·Llama 3.1 70B Instructlanguage·Llama 3.1 70B Instructmath·Llama 3.1 70B Instructreasoning·Llama 3.1 70B Instruct

Hype vs Reality

Attention vs performance

Gemma 2 27B

#220 by perf·#7 by attention

OVERHYPED

Llama 3.1 70B Instruct

#216 by perf·#18 by attention

QUIET

See full mindshare →

Best value

Llama 3.1 70B Instruct

1.6x better value than Gemma 2 27B

Gemma 2 27B

55.2 pts/$

$0.65/M

Llama 3.1 70B Instruct

90.7 pts/$

$0.40/M

Explore pricing →

Vendor risk

Who is behind the model

Google DeepMind

$4.20T·Tier 1

Low risk

Meta AI

$1.87T·Tier 1

Low risk

See the AI economy →

Head to head

13 benchmarks · 2 models

Gemma 2 27BLlama 3.1 70B Instruct

Chatbot Arena Elo · Overall

Llama 3.1 70B Instruct leads by +3.9

Gemma 2 27B

1289.4

Llama 3.1 70B Instruct

1293.3

Dtbench

Llama 3.1 70B Instruct leads by +20.0

Gemma 2 27B

13.3

Llama 3.1 70B Instruct

33.3

GPQA diamond

Llama 3.1 70B Instruct leads by +10.3

Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.

Gemma 2 27B

15.3

Llama 3.1 70B Instruct

25.6

BBH (HuggingFace)

Llama 3.1 70B Instruct leads by +6.7

Gemma 2 27B

49.3

Llama 3.1 70B Instruct

55.9

GPQA

Gemma 2 27B leads by +2.5

Gemma 2 27B

16.7

Llama 3.1 70B Instruct

14.2

IFEval

Llama 3.1 70B Instruct leads by +6.9

Gemma 2 27B

79.8

Llama 3.1 70B Instruct

86.7

MATH Level 5

Llama 3.1 70B Instruct leads by +14.2

Gemma 2 27B

23.9

Llama 3.1 70B Instruct

38.1

MMLU-PRO

Llama 3.1 70B Instruct leads by +9.5

Gemma 2 27B

38.4

Llama 3.1 70B Instruct

47.9

MUSR

Llama 3.1 70B Instruct leads by +8.6

Gemma 2 27B

9.1

Llama 3.1 70B Instruct

17.7

Lmca

Llama 3.1 70B Instruct leads by +9.1

Gemma 2 27B

8.3

Llama 3.1 70B Instruct

17.5

MATH level 5

Llama 3.1 70B Instruct leads by +8.8

MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.

Gemma 2 27B

27.9

Llama 3.1 70B Instruct

36.7

MMLU

Llama 3.1 70B Instruct leads by +5.9

Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.

Gemma 2 27B

67.6

Llama 3.1 70B Instruct

73.5

OTIS Mock AIME 2024-2025

Llama 3.1 70B Instruct leads by +2.2

OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.

Gemma 2 27B

1.3

Llama 3.1 70B Instruct

3.5

Full benchmark table

Benchmark	Gemma 2 27B	Llama 3.1 70B Instruct
Chatbot Arena Elo · Overall	1289.4	1293.3
Dtbench	13.3	33.3
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.	15.3	25.6
BBH (HuggingFace)	49.3	55.9
GPQA	16.7	14.2
IFEval	79.8	86.7
MATH Level 5	23.9	38.1
MMLU-PRO	38.4	47.9
MUSR	9.1	17.7
Lmca	8.3	17.5
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.	27.9	36.7
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.	67.6	73.5
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.	1.3	3.5

Pricing · per 1M tokens · projected $/mo at 10M tokens

Model	Input	Output	Context	Projected $/mo
Gemma 2 27B	$0.65	$0.65	8K tokens (~4 books)	$6.50
Llama 3.1 70B Instruct	$0.40	$0.40	131K tokens (~66 books)	$4.00

People also compared

GPT-5.5 Pro vs Llama 3.1 70B Instruct GPT-5.5 vs Llama 3.1 70B Instruct Claude Opus 5.5 vs Llama 3.1 70B Instruct Claude Mythos Preview vs Llama 3.1 70B Instruct DeepSeek V3.2 Speciale vs Llama 3.1 70B Instruct DeepSeek-V2 (MoE-236B, May 2024) vs Llama 3.1 70B Instruct Grok 3 Beta vs Llama 3.1 70B Instruct Llama 3.1 70B Instruct vs MiniMax M2