Enter opens the highlighted result. Esc closes.

Gemma 2 27B vs Qwen2.5 72B Instruct

Qwen2.5 72B Instruct costs 1.6x less per output token than Gemma 2 27B ($0.40 vs $0.65 per million). Updated October 21, 2026; 34 benchmarks have a result for both.

Replace Gemma 2 27B Replace Qwen2.5 72B Instruct
Gemma 2 27BGoogle
Coding
No data
Overall
No data
Output $/M
$0.65
3
Qwen2.5 72B InstructQwen
Coding
No data
Overall
26.5
Output $/M
$0.40
31
vs boards won of 34 shared

Gemma 2 27B or Qwen2.5 72B Instruct: which to pick

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

Pick Gemma 2 27B for 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 BQwen2.5 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
34
Gemma 2 27B only
2
Qwen2.5 72B Instruct only
19
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, Qwen2.5 72B Instruct not benchmarked.
Widest category
Math, 16.3 points apart on average over 4 shared benchmarks.
Widest single gap
MATH level 5: Gemma 2 27B 27.9% against Qwen2.5 72B Instruct 63.2%, 35.3 points apart on a 0 to 100 scale.
Output price
Gemma 2 27B $0.65 against Qwen2.5 72B Instruct $0.40 per million output tokens, 1.6x apart.
Context window
Gemma 2 27B takes 8K tokens, Qwen2.5 72B Instruct 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
CategoryGemma 2 27BBarsQwen2.5 72B InstructTies
Coding02
Intelligence01
Reasoning04
Math04
Knowledge05
General315
All shared boards331
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
Coding benchmarks for Gemma 2 27B and Qwen2.5 72B Instruct
BenchmarkGemma 2 27BQwen2.5 72B InstructLeader
LiveCodeBench (Artificial Analysis run)Not measured27.6%Only Qwen2.5 72B Instruct measured
Terminal-Bench Hard (Artificial Analysis run)Not measured4.5%Only Qwen2.5 72B Instruct measured
WeirdMLNot measured16.0%Only Qwen2.5 72B Instruct measured
LMArena Text: coding12111292Qwen2.5 72B Instruct
LMArena Text: software and IT12281292Qwen2.5 72B Instruct
Neither model has a result on the other 34 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Gemma 2 27B and Qwen2.5 72B Instruct
BenchmarkGemma 2 27BQwen2.5 72B InstructLeader
AA Intelligence IndexNot measured7.7Only Qwen2.5 72B Instruct measured
Epoch Capabilities Index122.1129.0Qwen2.5 72B Instruct
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Agentic work benchmarks for Gemma 2 27B and Qwen2.5 72B Instruct
BenchmarkGemma 2 27BQwen2.5 72B InstructLeader
τ²-Bench TelecomNot measured34.5%Only Qwen2.5 72B Instruct measured
METR time horizonsNot measured35.8%Only Qwen2.5 72B Instruct measured
BALROGNot measured16.2%Only Qwen2.5 72B Instruct measured
TheAgentCompanyNot measured5.7%Only Qwen2.5 72B Instruct measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for Gemma 2 27B and Qwen2.5 72B Instruct
BenchmarkGemma 2 27BQwen2.5 72B InstructLeader
GPQA Diamond (Artificial Analysis run)Not measured49.1%Only Qwen2.5 72B Instruct measured
Humanity's Last Exam (Artificial Analysis run)Not measured3.6%Only Qwen2.5 72B Instruct measured
GPQA Diamond (Epoch AI run)36.5%49.1%Qwen2.5 72B Instruct
BIG-Bench HardNot measured79.8%Only Qwen2.5 72B Instruct measured
LMArena Text: hard prompts11981271Qwen2.5 72B Instruct
LMArena Text: expert11711245Qwen2.5 72B Instruct
LMArena Text: hard prompts in English12061279Qwen2.5 72B 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 Qwen2.5 72B Instruct
BenchmarkGemma 2 27BQwen2.5 72B InstructLeader
AA Math IndexNot measured14.0Only Qwen2.5 72B Instruct measured
AIME 2025 (Artificial Analysis run)Not measured14.0%Only Qwen2.5 72B Instruct measured
OTIS Mock AIME1.4%8.1%Qwen2.5 72B Instruct
MATH level 527.9%63.2%Qwen2.5 72B Instruct
LMArena Text: math12121283Qwen2.5 72B Instruct
LMArena Text: mathematical work12211290Qwen2.5 72B 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 Qwen2.5 72B Instruct
BenchmarkGemma 2 27BQwen2.5 72B InstructLeader
LegalBench (Vals AI)68.0%Not measuredOnly Gemma 2 27B measured
MMLU Pro (Artificial Analysis run)Not measured72.0%Only Qwen2.5 72B Instruct measured
MMLU75.7%85.3%Qwen2.5 72B Instruct
AI2 Reasoning ChallengeNot measured94.5%Only Qwen2.5 72B Instruct measured
LMArena Text: science12281275Qwen2.5 72B Instruct
LMArena Text: medicine and healthcare11981258Qwen2.5 72B Instruct
LMArena Text: legal and government12411288Qwen2.5 72B Instruct
LMArena Text: business and finance12081253Qwen2.5 72B Instruct
Neither model has a result on the other 10 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 Qwen2.5 72B Instruct
BenchmarkGemma 2 27BQwen2.5 72B InstructLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index315
General benchmarks for Gemma 2 27B and Qwen2.5 72B Instruct
BenchmarkGemma 2 27BQwen2.5 72B InstructLeader
IFBenchNot measured36.9%Only Qwen2.5 72B Instruct measured
DTBench48.0%62.9%Qwen2.5 72B Instruct
LMCA7.1%13.4%Qwen2.5 72B Instruct
HellaSwagNot measured84.8%Only Qwen2.5 72B Instruct measured
WinoGrandeNot measured82.3%Only Qwen2.5 72B Instruct measured
PIQANot measured82.6%Only Qwen2.5 72B Instruct measured
LMArena Text12311269Qwen2.5 72B Instruct
LMArena Text: instruction following12061254Qwen2.5 72B Instruct
LMArena Text: creative writing12401221Gemma 2 27B
LMArena Text: English12421283Qwen2.5 72B Instruct
LMArena Text: non-English12171252Qwen2.5 72B Instruct
LMArena Text: Chinese12211273Qwen2.5 72B Instruct
LMArena Text: German12091234Qwen2.5 72B Instruct
LMArena Text: Japanese11751180Qwen2.5 72B Instruct
LMArena Text: Korean11741188Qwen2.5 72B Instruct
LMArena Text: French12481280Qwen2.5 72B Instruct
LMArena Text: Spanish12281255Qwen2.5 72B Instruct
LMArena Text: Russian12341264Qwen2.5 72B Instruct
LMArena Text: Polish1277Not measuredOnly Gemma 2 27B measured
LMArena Text: multi-turn12241272Qwen2.5 72B Instruct
LMArena Text: longer queries12301281Qwen2.5 72B Instruct
LMArena Text: writing and language12491247Gemma 2 27B
LMArena Text: entertainment and media12121211Gemma 2 27B
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 Gemma 2 27B and Qwen2.5 72B Instruct
BenchmarkGemma 2 27BQwen2.5 72B 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
Qwen2.5 72B Instruct$0.0006Fits in one request

Qwen2.5 72B Instruct costs less

Repository review

50K input + 3K output tokens

Gemma 2 27B$0.034Exceeds the context window
Qwen2.5 72B Instruct$0.019Exceeds the context window

Qwen2.5 72B Instruct costs less

Agent loop

200K input + 10K output tokens

Gemma 2 27B$0.137Exceeds the context window
Qwen2.5 72B Instruct$0.076Exceeds the context window

Qwen2.5 72B 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 Qwen2.5 72B Instruct
SpecificationGoogle Gemma 2 27BQwen2.5 72B Instruct
MakerGoogleQwen
WeightsOpen weightsOpen weights
ReleasedJuly 13, 2024September 19, 2024
Context window8K33K
Input $/Mtok$0.65$0.36
Output $/Mtok$0.65$0.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 2 27B better than Qwen2.5 72B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemma 2 27B for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Gemma 2 27B or Qwen2.5 72B Instruct?

Gemma 2 27B costs $0.65 per million input tokens and $0.65 per million output tokens; Qwen2.5 72B Instruct costs $0.36 and $0.40. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 2 27B or Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct, with 33K tokens against 8K.

How many benchmarks is the Gemma 2 27B vs Qwen2.5 72B Instruct comparison based on?

34 benchmarks have a result for both models as of October 21, 2026. Gemma 2 27B's coding index rests on 0 independent benchmarks and Qwen2.5 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next