Noometry

Model comparison

Gemini 3.1 Pro Preview vs gpt-oss-20b

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 32.5 on the Noometry Index. gpt-oss-20b costs 125× 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 . 28 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

gpt-oss-20b OpenAI

32.5

Rank #255 Confirmed

Summary

  • They share 28 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 9 categories and gpt-oss-20b 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 19.3.
  • The biggest single-benchmark swing is Terminal-Bench: 80.2% for Gemini 3.1 Pro Preview and 3.4% for gpt-oss-20b.
  • gpt-oss-20b is cheaper at $0.018 / $0.09 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-20b has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Pro Previewgpt-oss-20b
ProviderGoogleOpenAI
Noometry Index56.732.5
Released2026-02-192025-08-05
WeightsProprietaryOpen
Context window1.05M131K
Max output66K16K
Input $ / M tokens$2$0.018
Output $ / M tokens$12$0.09
Results tracked7134

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-20b: 37.6 (#192)

BenchmarkGemini 3.1 Pro Previewgpt-oss-20b
SciCode58.9%34.4%
WeirdML72.1%40.9%
LMArena Coding14841306
ALE-Bench1,161566.05
SWE-bench Verified75.6%—
DeepSWE11.7%—
LMArena WebDev1447—
GSO22.6%—
MirrorCode8.9%—
AlgoTune2.02—

Agentic & Tool Use Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.7 (#34), gpt-oss-20b: 9.3 (#154)

BenchmarkGemini 3.1 Pro Previewgpt-oss-20b
Terminal-Bench80.2%3.4%
APEX-Agents35.3%—
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—
METR Time Horizons77%—
Vending-Bench 23,774—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#12), gpt-oss-20b: 19.3 (#261)

BenchmarkGemini 3.1 Pro Previewgpt-oss-20b
CritPt17.7%1.4%
Chess Puzzles55%4%
LMArena Hard Prompts14851274
DTBench97.1%68%
LMCA53.8%14.5%
Epoch Capabilities Index154.77137.82
ARC-AGI-277.1%—
SimpleBench79.6%—
Kagi LLM Benchmark—53.2%
NYT Connections (extended)97.4%—
ARC-AGI-198%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
Mystery Game Puzzles34%—
ForecastBench59—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), gpt-oss-20b: 39.4 (#103)

BenchmarkGemini 3.1 Pro Previewgpt-oss-20b
OTIS Mock AIME 2024-202595.6%65.3%
LMArena Math14851317
FrontierMath (Tiers 1-3)59.6%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions86.5%—
ProofBench26%—
Omni-MATH—56.5%
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-20b: 34.6 (#195)

BenchmarkGemini 3.1 Pro Previewgpt-oss-20b
GPQA Diamond94.4%60.8%
LMArena Expert14851258
Humanity's Last Exam46.4%—
SimpleQA Verified73.5%—
MMLU-Pro—74%
Vectara Hallucination Rate10.4%—
GPQA (HELM)—59.4%

Multimodal Not comparable

Gemini 3.1 Pro Preview: 37.9 (#69), gpt-oss-20b: —

BenchmarkGemini 3.1 Pro Previewgpt-oss-20b
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-20b: 42.2 (#197)

BenchmarkGemini 3.1 Pro Previewgpt-oss-20b
LMArena Non-English14771268
LMArena Chinese15291314
LMArena German14911255
LMArena Japanese14931244
LMArena Korean14551236
LMArena Russian14981278
LMArena Spanish14791267
LMArena French1487—

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), gpt-oss-20b: 61.8 (#240)

BenchmarkGemini 3.1 Pro Previewgpt-oss-20b
LMArena Instruction Following14661236
IFEval—73.2%

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), gpt-oss-20b: 37.9 (#209)

BenchmarkGemini 3.1 Pro Previewgpt-oss-20b
LMArena Longer Query14831250
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-20b: 35.5 (#265)

BenchmarkGemini 3.1 Pro Previewgpt-oss-20b
LMArena Text14811287
LMArena Creative Writing14821201
EQ-Bench Creative Writing1491666
LMArena Multi-Turn14881268
WildBench—73.7%
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than gpt-oss-20b?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 32.5 on the Noometry Index. gpt-oss-20b costs 125× 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-20b?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or gpt-oss-20b better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 37.6 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-20b share?

28 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and gpt-oss-20b has 34.

Related comparisons

Go deeper