Noometry

Model comparison

Gemma 2 27B vs gpt-oss-20b

gpt-oss-20b is the stronger model overall, scoring 32.5 to 29.4 on the Noometry Index.

Last verified . 21 shared benchmarks.

Gemma 2 27B Google

29.4

Rank #312 Confirmed

gpt-oss-20b OpenAI

32.5

Rank #255 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 39.4 to 10.7.
  • 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 Index29.432.5
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: 34.1 (#246), gpt-oss-20b: 37.6 (#192)

BenchmarkGemma 2 27Bgpt-oss-20b
LMArena Coding12111306
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: 9.3 (#154)

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

Reasoning gpt-oss-20b leads

Gemma 2 27B: 15.3 (#315), gpt-oss-20b: 19.3 (#261)

BenchmarkGemma 2 27Bgpt-oss-20b
LMArena Hard Prompts11981274
DTBench48%68%
LMCA7.1%14.5%
Epoch Capabilities Index122.08137.82
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: 10.7 (#311), gpt-oss-20b: 39.4 (#103)

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: 19.0 (#280), gpt-oss-20b: 34.6 (#195)

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: 38.6 (#226), gpt-oss-20b: 42.2 (#197)

BenchmarkGemma 2 27Bgpt-oss-20b
LMArena Non-English12171268
LMArena Chinese12211314
LMArena German12091255
LMArena Japanese11751244
LMArena Korean11741236
LMArena Russian12341278
LMArena Spanish12281267
LMArena French1247—

Instruction Following gpt-oss-20b leads

Gemma 2 27B: 60.5 (#249), gpt-oss-20b: 61.8 (#240)

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 (#218), gpt-oss-20b: 37.9 (#209)

BenchmarkGemma 2 27Bgpt-oss-20b
LMArena Longer Query12311250

Writing & Preference Gemma 2 27B leads

Gemma 2 27B: 44.2 (#225), gpt-oss-20b: 35.5 (#265)

BenchmarkGemma 2 27Bgpt-oss-20b
LMArena Text12311287
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 32.5 to 29.4 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: 37.6 versus 34.1 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