Noometry

Model comparison

Gemini 3.1 Pro Preview vs gpt-oss-120b

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 36.3 on the Noometry Index. gpt-oss-120b costs 64× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Last verified . 36 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

gpt-oss-120b OpenAI

36.3

Rank #217 Confirmed

Summary

  • They share 36 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 9 categories and gpt-oss-120b in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 20.0.
  • The biggest single-benchmark swing is Terminal-Bench: 80.2% for Gemini 3.1 Pro Preview and 18.7% for gpt-oss-120b.
  • gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 131K.
  • gpt-oss-120b has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Pro Previewgpt-oss-120b
ProviderGoogleOpenAI
Noometry Index56.736.3
Released2026-02-192025-08-05
WeightsProprietaryOpen
Context window1.05M131K
Max output66K41K
Input $ / M tokens$2$0.037
Output $ / M tokens$12$0.17
Results tracked7148

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

Category by category

Coding Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 42.5 (#99), gpt-oss-120b: 33.5 (#256)

BenchmarkGemini 3.1 Pro Previewgpt-oss-120b
SciCode58.9%36%
WeirdML72.1%48.2%
LMArena Coding14841380
ALE-Bench1,161575.62
AlgoTune2.021.41
SWE-bench Verified75.6%—
DeepSWE11.7%—
SWE-bench Verified (bash only)—26%
Aider Polyglot—41.8%
LMArena WebDev1447—
GSO22.6%—
MirrorCode8.9%—

Agentic & Tool Use Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.7 (#34), gpt-oss-120b: 12.2 (#153)

BenchmarkGemini 3.1 Pro Previewgpt-oss-120b
Terminal-Bench80.2%18.7%
APEX-Agents35.3%4.4%
METR Time Horizons77%56.6%
Vending-Bench 23,774-21.53
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#12), gpt-oss-120b: 20.0 (#245)

BenchmarkGemini 3.1 Pro Previewgpt-oss-120b
SimpleBench79.6%22.1%
CritPt17.7%1.1%
Chess Puzzles55%20%
LMArena Hard Prompts14851364
Mystery Game Puzzles34%2%
DTBench97.1%76.3%
LMCA53.8%22.1%
Epoch Capabilities Index154.77139.93
ARC-AGI-277.1%—
Kagi LLM Benchmark—58.6%
NYT Connections (extended)97.4%—
ARC-AGI-198%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
Surface Evolver Bench—25%
ForecastBench59—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), gpt-oss-120b: 52.5 (#50)

BenchmarkGemini 3.1 Pro Previewgpt-oss-120b
OTIS Mock AIME 2024-202595.6%88.9%
LMArena Math14851389
FrontierMath (Tiers 1-3)59.6%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions86.5%—
ProofBench26%—
Omni-MATH—68.8%
FrontierMath (Feb 2025 set)36.9%—
FrontierMath Tier 4 (v1)16.7%—

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), gpt-oss-120b: 42.4 (#96)

BenchmarkGemini 3.1 Pro Previewgpt-oss-120b
GPQA Diamond94.4%75.8%
Vectara Hallucination Rate10.4%14.2%
LMArena Expert14851356
Humanity's Last Exam46.4%—
SimpleQA Verified73.5%—
MMLU-Pro—79.5%
Confabulations—15.7%
GPQA (HELM)—68.4%

Multimodal Not comparable

Gemini 3.1 Pro Preview: 37.9 (#69), gpt-oss-120b: —

BenchmarkGemini 3.1 Pro Previewgpt-oss-120b
LMArena Vision1296—
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.0 (#12), gpt-oss-120b: 48.0 (#147)

BenchmarkGemini 3.1 Pro Previewgpt-oss-120b
LMArena Non-English14771351
LMArena Chinese15291385
LMArena French14871369
LMArena German14911353
LMArena Japanese14931331
LMArena Korean14551282
LMArena Russian14981343
LMArena Spanish14791389

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), gpt-oss-120b: 69.3 (#173)

BenchmarkGemini 3.1 Pro Previewgpt-oss-120b
LMArena Instruction Following14661318
IFEval—83.6%

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), gpt-oss-120b: 31.4 (#278)

BenchmarkGemini 3.1 Pro Previewgpt-oss-120b
LMArena Longer Query14831319
Fiction.LiveBench—44.4%
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.1 (#37), gpt-oss-120b: 46.5 (#217)

BenchmarkGemini 3.1 Pro Previewgpt-oss-120b
LMArena Text14811365
LMArena Creative Writing14821275
EQ-Bench Creative Writing1491961
LMArena Multi-Turn14881340
Short-Story Creative Writing—77.1%
WildBench—84.5%
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than gpt-oss-120b?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 36.3 on the Noometry Index. gpt-oss-120b costs 64× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.1 Pro Preview 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 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or gpt-oss-120b better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 131K.

How many benchmarks do Gemini 3.1 Pro Preview and gpt-oss-120b share?

36 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and gpt-oss-120b has 48.

Related comparisons

Go deeper