Noometry

Model comparison

Gemini 2.5 Pro vs gpt-oss-120b

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 36.3 on the Noometry Index. gpt-oss-120b costs 49× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Last verified . 45 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

gpt-oss-120b OpenAI

36.3

Rank #217 Confirmed

Summary

  • They share 45 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 8 categories and gpt-oss-120b in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Gemini 2.5 Pro leads 59.8 to 31.4.
  • The biggest single-benchmark swing is Fiction.LiveBench: 91.7% for Gemini 2.5 Pro and 44.4% for gpt-oss-120b.
  • gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
  • Gemini 2.5 Pro accepts more context: 1.05M tokens versus 131K.
  • gpt-oss-120b has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 Progpt-oss-120b
ProviderGoogleOpenAI
Noometry Index45.036.3
Released2025-03-252025-08-05
WeightsProprietaryOpen
Context window1.05M131K
Max output66K41K
Input $ / M tokens$1.25$0.037
Output $ / M tokens$10$0.17
Results tracked7848

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

Category by category

Coding Gemini 2.5 Pro leads

Gemini 2.5 Pro: 42.4 (#101), gpt-oss-120b: 33.5 (#256)

BenchmarkGemini 2.5 Progpt-oss-120b
SWE-bench Verified (bash only)53.6%26%
Aider Polyglot83.1%41.8%
SciCode42.8%36%
WeirdML54%48.2%
LMArena Coding14521380
ALE-Bench785.52575.62
AlgoTune1.511.41
SWE-bench Verified57.6%—
LMArena WebDev1227—
GSO3.9%—
LiveBench Coding85.9%—
CadEval64%—

Agentic & Tool Use Gemini 2.5 Pro leads

Gemini 2.5 Pro: 29.2 (#88), gpt-oss-120b: 12.2 (#153)

BenchmarkGemini 2.5 Progpt-oss-120b
Terminal-Bench32.6%18.7%
METR Time Horizons55.4%56.6%
Vending-Bench 2573.64-21.53
APEX-Agents—4.4%
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
τ²-bench Banking13.7%—
DeepResearch Bench42.8%—
BALROG43.3%—
LMArena Search1142—

Reasoning Gemini 2.5 Pro leads

Gemini 2.5 Pro: 28.8 (#99), gpt-oss-120b: 20.0 (#245)

BenchmarkGemini 2.5 Progpt-oss-120b
SimpleBench62.4%22.1%
Kagi LLM Benchmark70.3%58.6%
CritPt2%1.1%
Chess Puzzles20%20%
LMArena Hard Prompts14551364
DTBench82.4%76.3%
LMCA34.8%22.1%
Epoch Capabilities Index145.32139.93
ARC-AGI-24.9%—
ARC-AGI-141%—
EnigmaEval5.6%—
LiveBench Reasoning89.8%—
Mystery Game Puzzles—2%
LiveBench Data Analysis79.9%—
Surface Evolver Bench—25%
ForecastBench61.3—
LiveBench82.3%—

Math gpt-oss-120b leads

Gemini 2.5 Pro: 32.5 (#213), gpt-oss-120b: 52.5 (#50)

BenchmarkGemini 2.5 Progpt-oss-120b
OTIS Mock AIME 2024-202584.7%88.9%
Omni-MATH41.6%68.8%
LMArena Math14501389
FrontierMath (Tiers 1-3)24.6%—
FrontierMath Tier 40%—
LiveBench Math90.2%—
MATH Level 595.9%—
FrontierMath (Feb 2025 set)14.1%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Gemini 2.5 Pro leads

Gemini 2.5 Pro: 56.0 (#46), gpt-oss-120b: 42.4 (#96)

BenchmarkGemini 2.5 Progpt-oss-120b
GPQA Diamond85.3%75.8%
MMLU-Pro86.3%79.5%
Confabulations10.6%15.7%
Vectara Hallucination Rate7%14.2%
GPQA (HELM)74.9%68.4%
LMArena Expert14521356
Humanity's Last Exam21.6%—

Multimodal Not comparable

Gemini 2.5 Pro: 45.2 (#18), gpt-oss-120b: —

BenchmarkGemini 2.5 Progpt-oss-120b
LMArena Vision1263—
GeoBench86%—
VPCT48%—
LMArena Document1421—
SpatialViz-Bench44.7%—

Multilingual Gemini 2.5 Pro leads

Gemini 2.5 Pro: 55.3 (#31), gpt-oss-120b: 48.0 (#147)

BenchmarkGemini 2.5 Progpt-oss-120b
LMArena Non-English14511351
LMArena Chinese15071385
LMArena French14721369
LMArena German14871353
LMArena Japanese14611331
LMArena Korean14341282
LMArena Russian14611343
LMArena Spanish14731389

Instruction Following Gemini 2.5 Pro leads

Gemini 2.5 Pro: 75.0 (#75), gpt-oss-120b: 69.3 (#173)

BenchmarkGemini 2.5 Progpt-oss-120b
IFEval84%83.6%
LMArena Instruction Following14371318
LiveBench Instruction Following80.6%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), gpt-oss-120b: 31.4 (#278)

BenchmarkGemini 2.5 Progpt-oss-120b
Fiction.LiveBench91.7%44.4%
LMArena Longer Query14491319

Writing & Preference Gemini 2.5 Pro leads

Gemini 2.5 Pro: 63.7 (#62), gpt-oss-120b: 46.5 (#217)

BenchmarkGemini 2.5 Progpt-oss-120b
LMArena Text14581365
LMArena Creative Writing14541275
Short-Story Creative Writing83.8%77.1%
EQ-Bench Creative Writing1421961
WildBench85.7%84.5%
LMArena Multi-Turn14531340
LiveBench Language67.8%—

Frequently asked questions

Is Gemini 2.5 Pro better than gpt-oss-120b?

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 36.3 on the Noometry Index. gpt-oss-120b costs 49× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Which is cheaper, Gemini 2.5 Pro or gpt-oss-120b?

gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

Is Gemini 2.5 Pro or gpt-oss-120b better for coding?

Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 131K.

How many benchmarks do Gemini 2.5 Pro and gpt-oss-120b share?

45 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and gpt-oss-120b has 48.

Related comparisons

Go deeper