Noometry

Model comparison

Gemma 2 27B vs gpt-oss-20b

gpt-oss-20b is the stronger model overall, scoring 32.1 to 29.2 on the Noometry Index.

Last verified . 21 shared benchmarks.

Gemma 2 27B Google

29.2

Rank #302 Confirmed

gpt-oss-20b OpenAI

32.1

Rank #249 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Gemma 2 27B scores higher in 1 category and gpt-oss-20b in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where gpt-oss-20b leads 37.6 to 10.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.4% for Gemma 2 27B and 65.3% for gpt-oss-20b.
  • gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
  • gpt-oss-20b accepts more context: 131K tokens versus 8K.

Side by side

Gemma 2 27Bgpt-oss-20b
ProviderGoogleOpenAI
Noometry Index29.232.1
Released2024-06-242025-08-05
WeightsOpenOpen
Context window8K131K
Max output2K16K
Input $ / M tokens$0.65$0.018
Output $ / M tokens$0.65$0.09
Results tracked3434

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding gpt-oss-20b leads

Gemma 2 27B: 33.5 (#243), gpt-oss-20b: 37.1 (#185)

BenchmarkGemma 2 27Bgpt-oss-20b
LMArena Coding12111307
SciCode—34.4%
WeirdML—40.9%
BigCodeBench Instruct42.8%—
LiveBench Coding36%—
BigCodeBench Complete52.5%—
ALE-Bench—566.05

Agentic & Tool Use Not comparable

Gemma 2 27B: —, gpt-oss-20b: 9.2 (#146)

BenchmarkGemma 2 27Bgpt-oss-20b
Terminal-Bench—3.4%

Reasoning gpt-oss-20b leads

Gemma 2 27B: 14.8 (#313), gpt-oss-20b: 18.8 (#251)

BenchmarkGemma 2 27Bgpt-oss-20b
LMArena Hard Prompts11991274
DTBench48%68%
LMCA7.1%14.5%
Epoch Capabilities Index122.06137.81
Kagi LLM Benchmark—53.2%
CritPt—1.4%
Chess Puzzles—4%
LiveBench Reasoning28.1%—
LiveBench Data Analysis47.9%—
LiveBench38.2%—

Math gpt-oss-20b leads

Gemma 2 27B: 10.0 (#306), gpt-oss-20b: 37.6 (#93)

BenchmarkGemma 2 27Bgpt-oss-20b
OTIS Mock AIME 2024-20251.4%65.3%
LMArena Math12121317
Omni-MATH—56.5%
LiveBench Math26.5%—
MATH Level 527.9%—

Knowledge gpt-oss-20b leads

Gemma 2 27B: 18.9 (#275), gpt-oss-20b: 34.6 (#186)

BenchmarkGemma 2 27Bgpt-oss-20b
GPQA Diamond36.5%60.8%
LMArena Expert11721258
MMLU-Pro—74%
Confabulations27.1%—
GPQA (HELM)—59.4%
MMLU75.7%—

Multilingual gpt-oss-20b leads

Gemma 2 27B: 38.8 (#221), gpt-oss-20b: 42.4 (#192)

BenchmarkGemma 2 27Bgpt-oss-20b
LMArena Non-English12171269
LMArena Chinese12211311
LMArena German12091249
LMArena Japanese11751245
LMArena Korean11741239
LMArena Russian12341279
LMArena Spanish12281267
LMArena French1246—

Instruction Following gpt-oss-20b leads

Gemma 2 27B: 60.7 (#244), gpt-oss-20b: 62.0 (#235)

BenchmarkGemma 2 27Bgpt-oss-20b
LMArena Instruction Following12061236
LiveBench Instruction Following58.1%—
IFEval—73.2%

Long Context Too close to call

Gemma 2 27B: 37.3 (#213), gpt-oss-20b: 37.9 (#203)

BenchmarkGemma 2 27Bgpt-oss-20b
LMArena Longer Query12311251

Writing & Preference Gemma 2 27B leads

Gemma 2 27B: 44.4 (#220), gpt-oss-20b: 35.8 (#260)

BenchmarkGemma 2 27Bgpt-oss-20b
LMArena Text12311288
LMArena Creative Writing12411201
LMArena Multi-Turn12241268
EQ-Bench Creative Writing—666
WildBench—73.7%
LiveBench Language32.6%—

Frequently asked questions

Is Gemma 2 27B better than gpt-oss-20b?

gpt-oss-20b is the stronger model overall, scoring 32.1 to 29.2 on the Noometry Index.

Which is cheaper, Gemma 2 27B or gpt-oss-20b?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.

Is Gemma 2 27B or gpt-oss-20b better for coding?

gpt-oss-20b scores higher on coding benchmarks: 37.1 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

gpt-oss-20b does, with 131K tokens against 8K.

How many benchmarks do Gemma 2 27B and gpt-oss-20b share?

21 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and gpt-oss-20b has 34.

Related comparisons

Go deeper