GPT-5.6 LunavsGemini 3.5 Flash
Across 6 shared benchmarks, GPT-5.6 Luna leads overall: GPT-5.6 Luna wins 4, Gemini 3.5 Flash wins 2, with 0 ties and an average score difference of +13.06.
GPT-5.6 Luna
OpenAI · 2026-06-26 · Reasoning model
Gemini 3.5 Flash
Google Deep Mind · 2026-06-20 · Multimodal model
GPT-5.6 Luna4 wins(67%)(33%)2 winsGemini 3.5 Flash
Benchmark scores
Grouped by capability, sorted by largest gap within each. 6 shared benchmarks.
Math and Reasoning
GPT-5.6 Luna 2/2| Benchmark | GPT-5.6 Luna | Gemini 3.5 Flash | Diff |
|---|---|---|---|
| FrontierMath Tier 4 v2 | 60.987 / 34最高（无工具） | 26.8318 / 34Thinking High (No Tools) | +34.15 |
| FrontierMath v2 | 82.118 / 34最高（无工具） | 62.8118 / 34Thinking High (No Tools) | +19.30 |
AI Agent - Tool Usage
GPT-5.6 Luna 1/1| Benchmark | GPT-5.6 Luna | Gemini 3.5 Flash | Diff |
|---|---|---|---|
| Terminal-Bench 2.1 | 84.7010 / 44最高（无工具） | 76.2023 / 44Thinking High (With Tools) | +8.50 |
Coding and Software Engineer
GPT-5.6 Luna 1/1| Benchmark | GPT-5.6 Luna | Gemini 3.5 Flash | Diff |
|---|---|---|---|
| DeepSWE | 67.206 / 27极高强度思考（工具） | 3723 / 27Thinking Medium (With Tools) | +30.20 |
General Evaluation
Gemini 3.5 Flash 1/1| Benchmark | GPT-5.6 Luna | Gemini 3.5 Flash | Diff |
|---|---|---|---|
| GPQA Diamond | 91.6027 / 226最高（无工具） | 92.8019 / 226Thinking High (No Tools) | -1.20 |
General Knowledge
Gemini 3.5 Flash 1/1| Benchmark | GPT-5.6 Luna | Gemini 3.5 Flash | Diff |
|---|---|---|---|
| ARC-AGI-2 | 59.5020 / 62最高（无工具） | 72.1013 / 62Thinking High (With Tools) | -12.60 |
Specs
| Field | GPT-5.6 Luna | Gemini 3.5 Flash |
|---|---|---|
| Publisher | OpenAI | Google Deep Mind |
| Release date | 2026-06-26 | 2026-06-20 |
| Model type | Reasoning model | Multimodal model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1.05M | 1M |
| Max output | 128K | 64K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | GPT-5.6 Luna | Gemini 3.5 Flash |
|---|---|---|
| Text input | $1 / 1M tokens | $1.5 / 1M tokens |
| Text output | $6 / 1M tokens | $9 / 1M tokens |
| Cache read | $0.1 / 1M tokens | $0.15 / 1M tokens |
| Cache write | $1.25 / 1M tokens | Not public |
Summary
- GPT-5.6 Lunaleads in:Math and Reasoning (2/2), AI Agent - Tool Usage (1/1), Coding and Software Engineer (1/1)
- Gemini 3.5 Flashleads in:General Evaluation (1/1), General Knowledge (1/1)
On average across the 6 shared benchmarks, GPT-5.6 Luna scores 13.06 higher.
Largest single-benchmark gap: FrontierMath Tier 4 v2 — GPT-5.6 Luna 60.98 vs Gemini 3.5 Flash 26.83 (+34.15).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.