Noometry

Model comparison

Gemini 3.1 Pro Preview vs GPT-5.6 Luna

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 54.6 on the Noometry Index. GPT-5.6 Luna costs 10× 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 . 48 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

GPT-5.6 Luna OpenAI

54.6

Rank #30 Confirmed

Summary

  • They share 48 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 6 categories and GPT-5.6 Luna in 4 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 47.6.
  • The biggest single-benchmark swing is DeepSWE: 11.7% for Gemini 3.1 Pro Preview and 67.2% for GPT-5.6 Luna.
  • GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
  • GPT-5.6 Luna accepts more context: 1.05M tokens versus 1.05M.

Side by side

Gemini 3.1 Pro PreviewGPT-5.6 Luna
ProviderGoogleOpenAI
Noometry Index56.754.6
Released2026-02-192026-07-09
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output66K128K
Input $ / M tokens$2$0.20
Output $ / M tokens$12$1.20
Results tracked7152

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

Category by category

Coding GPT-5.6 Luna leads

Gemini 3.1 Pro Preview: 42.5 (#99), GPT-5.6 Luna: 54.5 (#28)

BenchmarkGemini 3.1 Pro PreviewGPT-5.6 Luna
DeepSWE11.7%67.2%
LMArena WebDev14471519
SciCode58.9%53.6%
WeirdML72.1%60.9%
LMArena Coding14841466
ALE-Bench1,1611,667
SWE-bench Verified75.6%—
FrontierCode—39.8%
CursorBench—35.9%
GSO22.6%—
MirrorCode8.9%—
AlgoTune2.02—

Agentic & Tool Use Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.7 (#34), GPT-5.6 Luna: 34.4 (#45)

BenchmarkGemini 3.1 Pro PreviewGPT-5.6 Luna
APEX-Agents35.3%43%
BALROG57%45.6%
GDP.pdf17%22.7%
Vending-Bench 23,7744,095
Terminal-Bench80.2%—
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
ExploitBench26.1%—
GBAEval0.8%—
LMArena Search1211—
METR Time Horizons77%—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#12), GPT-5.6 Luna: 47.6 (#43)

BenchmarkGemini 3.1 Pro PreviewGPT-5.6 Luna
ARC-AGI-277.1%59.5%
SimpleBench79.6%46.8%
NYT Connections (extended)97.4%69.4%
ARC-AGI-198%88%
CritPt17.7%20.6%
Chess Puzzles55%40%
LMArena Hard Prompts14851451
Mystery Game Puzzles34%21%
DTBench97.1%89.1%
LMCA53.8%48.5%
Epoch Capabilities Index154.77156.39
Kagi LLM Benchmark—49.1%
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
Surface Evolver Bench—61.9%
ForecastBench59—

Math GPT-5.6 Luna leads

Gemini 3.1 Pro Preview: 62.1 (#34), GPT-5.6 Luna: 77.7 (#14)

BenchmarkGemini 3.1 Pro PreviewGPT-5.6 Luna
FrontierMath (Tiers 1-3)59.6%82.1%
FrontierMath Tier 426.8%61%
OTIS Mock AIME 2024-202595.6%98.3%
ProofBench26%60%
LMArena Math14851458
MathArena Final-Answer Competitions86.5%—
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-5.6 Luna: 58.5 (#34)

BenchmarkGemini 3.1 Pro PreviewGPT-5.6 Luna
GPQA Diamond94.4%91.6%
SimpleQA Verified73.5%41%
LMArena Expert14851478
Humanity's Last Exam46.4%—
Vectara Hallucination Rate10.4%—

Multimodal GPT-5.6 Luna leads

Gemini 3.1 Pro Preview: 37.9 (#69), GPT-5.6 Luna: 42.7 (#28)

BenchmarkGemini 3.1 Pro PreviewGPT-5.6 Luna
LMArena Vision12961258
Blueprint-Bench 226.5%22.6%
Furniture Assembly26.7%42.5%
LMArena Document14441457

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.0 (#12), GPT-5.6 Luna: 52.8 (#78)

BenchmarkGemini 3.1 Pro PreviewGPT-5.6 Luna
LMArena Non-English14771417
LMArena Chinese15291470
LMArena French14871456
LMArena German14911454
LMArena Japanese14931411
LMArena Korean14551415
LMArena Russian14981428
LMArena Spanish14791448

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), GPT-5.6 Luna: 75.6 (#57)

BenchmarkGemini 3.1 Pro PreviewGPT-5.6 Luna
LMArena Instruction Following14661437

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), GPT-5.6 Luna: 43.9 (#82)

BenchmarkGemini 3.1 Pro PreviewGPT-5.6 Luna
LMArena Longer Query14831436
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference GPT-5.6 Luna leads

Gemini 3.1 Pro Preview: 66.1 (#37), GPT-5.6 Luna: 68.0 (#29)

BenchmarkGemini 3.1 Pro PreviewGPT-5.6 Luna
LMArena Text14811431
LMArena Creative Writing14821396
EQ-Bench Creative Writing14911829
EQ-Bench 411421156
LMArena Multi-Turn14881434

Frequently asked questions

Is Gemini 3.1 Pro Preview better than GPT-5.6 Luna?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 54.6 on the Noometry Index. GPT-5.6 Luna costs 10× 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-5.6 Luna?

GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or GPT-5.6 Luna better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 42.5 in the Noometry coding category.

Which has the bigger context window?

GPT-5.6 Luna does, with 1.05M tokens against 1.05M.

How many benchmarks do Gemini 3.1 Pro Preview and GPT-5.6 Luna share?

48 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and GPT-5.6 Luna has 52.

Related comparisons

Go deeper