Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Gemini 3.5 Flash vs GPT-5.6 Luna

45 SHARED BENCHMARKS

Across 45 shared benchmarks, Gemini 3.5 Flash scores higher on 23 and GPT-5.6 Luna on 22. The widest gap is AA-Omniscience · Non-hallucination, where Gemini 3.5 Flash scores 37.8 against 7.4. GPT-5.6 Luna is the cheaper of the two on tracked API pricing ($0.20 against $1.50 per million input tokens).

GOOGLEVSOPENAI45 SHARED23–22 HEAD-TO-HEADNEWEST SCORE ADDED

At a glance

MakerGoogleOpenAI
Released
Price per 1M tokens input / output$1.50 / $9.00$0.20 / $1.20
Cost of 1M in + 1M out$10.50$1.40 7.5× less
Head-to-head of 45 shared benchmarks23 wins22 wins
Scores tracked independently verified132 29 ◆201 43 ◆

Release dates per Artificial Analysis. Prices: Google's own price page for Gemini 3.5 Flash; OpenAI's own price page for GPT-5.6 Luna. ◆ = independently verified score.

Where each leadsby capability area · benchmark wins

AreaGemini 3.5 FlashWINSGPT-5.6 Luna
Reasoning42Gemini 3.5 Flash leads 4 of 6 · widest: SimpleBench 76.7 vs 46.8
Coding24GPT-5.6 Luna leads 4 of 6 · widest: SWE-bench Pro 55.1 vs 62.7
Agentic42Gemini 3.5 Flash leads 4 of 6 · widest: AA ApexAgents 47.1 vs 35.8
Factuality30Gemini 3.5 Flash leads 3 of 3 · widest: AA-Omniscience · Non-hallucination 37.8 vs 7.4
Instruction Following10Gemini 3.5 Flash leads 1 of 1 · widest: LiveBench · Instruction Following 75.6 vs 60.1
Long Context02GPT-5.6 Luna leads 2 of 2 · widest: MRCR v2 8 needle 128k (average) 26.6 vs 74.8
Math14GPT-5.6 Luna leads 4 of 5 · widest: FrontierMath Tier 4 26.8 vs 58.5
Multimodal30Gemini 3.5 Flash leads 3 of 3 · widest: MMMU-Pro 84.3 vs 78.6

Biggest gaps

Gemini 3.5 Flash pulls furthest ahead on

  1. AA-Omniscience · Non-hallucination37.8 vs 7.4
  2. SimpleBench76.7 vs 46.8
  3. SimpleQA Verified66.2 vs 41

GPT-5.6 Luna pulls furthest ahead on

  1. MRCR v2 8 needle 128k (average)74.8 vs 26.6
  2. FrontierMath Tier 458.5 vs 26.8
  3. Terminal-Bench 4.011.6 vs 6.6

Every shared benchmark45 · grouped by area

Reasoning 6

ARC-AGI-272.1◆ 59.6
CritPt13.120.6
GPQA Diamond92.291.1
SimpleBench76.7 ◆◆ 46.8

Coding 6

Agentic 6

GDPVal34.247.2
Terminal-Bench 4.06.611.6

Instruction Following 1

Long Context 2

Math 5

AIME 202695 ◆97.6
HMMT Feb. 202695.5 ◆98.5
LiveBench · Mathematics88.2 ◆◆ 87.2

Multimodal 3

LMArena · Vision1310 ◆◆ 1259
CharXiv (RQ)84.282.7
MMMU-Pro84.378.6

Other shared benchmarks 13

Each score is the one the model's own page shows — the most authoritative tracked result for that benchmark, on the benchmark's standard methodology (source-attributed). ↓ marks lower-is-better metrics; ◆ an independently verified score. Open either model for its full surface, provenance and pricing. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (google-official, openai-official), otherwise the lowest tracked offer.

Compare Gemini 3.5 Flash withALL PAIRINGS →

Compare GPT-5.6 Luna withALL PAIRINGS →