Gemini 3.6 Flash vs GPT-6 Luna
| Spec | Gemini 3.6 Flash | GPT-6 Luna |
|---|---|---|
| Respan Index | 45.6 (#53) | 48.6 (#45) |
| Blended price per 1M | $1.5 | $0.2 |
| Context window | 1.0M | 1.1M |
| Input / output per 1M | $0.75 / $3.75 | $0.1 / $0.5 |
| Max output | 66K | 128K |
| Input | text, vision, audio | text, vision |
| Released | 2026-07-21 | 2026-09-22 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Gemini 3.6 Flash | GPT-6 Luna |
|---|---|---|
| Coding | 22.3 Gemini 3.6 Flash | 28.4 GPT-6 Luna |
| Agents | 58.4 Gemini 3.6 Flash | 60.0 GPT-6 Luna |
| Reasoning | 42.6 Gemini 3.6 Flash | 57.1 GPT-6 Luna |
| Knowledge & language | 65.3 Gemini 3.6 Flash | 38.9 GPT-6 Luna |
| Human preference | 55.0 Gemini 3.6 Flash | 55.6 GPT-6 Luna |
Benchmarks both report
GPT-6 Luna leads on 12 of the 23 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Gemini 3.6 Flash | GPT-6 Luna |
|---|---|---|
| LMArena Elo | 1483 | 1441 |
| LMArena WebDev (LMArena) | 1538 | 1578 |
| MirrorCode (Epoch AI) | 23.3% | 26.7% |
| LMArena Vision (LMArena) | 1280 | 1235 |
| Chess Puzzles (Epoch AI) | 42% | 36% |
| LMArena Agent (LMArena) | -0.0445 | 0.0064 |
| APEX-Agents (Mercor) | 46.9% | 44.3% |
| FrontierMath Tier 4 v2 (Epoch AI) | 22% | 56.1% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 58.9% | 78.9% |
| Furniture Assembly (Epoch AI) | 23.3% | 44.2% |
| GPQA Diamond | 94.1% | 90.5% |
| LiveBench Agentic Coding (LiveBench) | 43.4% | 51.2% |
| LiveBench Coding (LiveBench) | 77.9% | 79% |
| LiveBench Data Analysis (LiveBench) | 63% | 73.4% |
| LiveBench Instruction Following (LiveBench) | 75.4% | 55.9% |
| LiveBench Language (LiveBench) | 83.9% | 73.8% |
| LiveBench Mathematics (LiveBench) | 86.4% | 89.1% |
| LiveBench Reasoning (LiveBench) | 85.1% | 81.8% |
| Mystery Game Puzzles (Epoch AI) | 30% | 7% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 94.2% | 98.9% |
| SAGE (Vals AI) | 48.7% | 48.1% |
| SimpleQA Verified | 66.2% | 41.4% |
| DeepSWE v1.1 | 49% | 66.6% |
FAQ
Is Gemini 3.6 Flash better than GPT-6 Luna?
GPT-6 Luna scores 48.6 on the Respan Index (#45), ahead of Gemini 3.6 Flash at 45.6 (#53). GPT-6 Luna leads on 12 of the 23 benchmarks both report.
Which is cheaper, Gemini 3.6 Flash or GPT-6 Luna?
Gemini 3.6 Flash lists at $0.75 input and $3.75 output per 1M tokens; GPT-6 Luna at $0.1 and $0.5. GPT-6 Luna is 7.5x cheaper per token at list price.
Which has the larger context window?
Gemini 3.6 Flash accepts 1.0M tokens and GPT-6 Luna 1.1M tokens.
Compare other models
- vsGemini 3.6 Flash vs Gemini 3.5 Flash
- vsGemini 3.7 Flash vs Gemini 3.6 Flash
- vsGPT-6 Luna vs GPT-5.6 Luna
- vsGemini 3.8 Flash vs Gemini 3.6 Flash
- vsGPT-6 Luna vs DeepSeek V4 Flash
- vsGemini 3.6 Flash vs Muse Spark 1.2
- vsGemini 3.6 Flash vs DeepSeek V4 Flash
- vsGemini 3.6 Flash vs Grok 4.5
- vsGPT-6 Luna vs DeepSeek V4 Pro
- vsGPT-6 Luna vs GPT-5.4