Model comparison
Gemini 3.5 Flash Lite vs GPT-6 Luna
GPT-6 Luna is the stronger model overall, scoring 53.3 to 41.5 on the Noometry Index.
Last verified . 37 shared benchmarks.
GoogleSummary
- They share 37 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 4 categories and GPT-6 Luna in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 25.9.
- The biggest single-benchmark swing is FrontierMath Tier 4: 0% for Gemini 3.5 Flash Lite and 56.1% for GPT-6 Luna.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.30 / $2.50 for Gemini 3.5 Flash Lite.
- GPT-6 Luna accepts more context: 1.05M tokens versus 1.05M.
Side by side
| Gemini 3.5 Flash Lite | GPT-6 Luna | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 41.5 | 53.3 |
| Released | 2026-07-21 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.30 | $0.10 |
| Output $ / M tokens | $2.50 | $0.50 |
| Results tracked | 39 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
Gemini 3.5 Flash Lite: 42.4 (#104), GPT-6 Luna: 55.5 (#25)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6 Luna |
|---|---|---|
| LMArena WebDev | 1440 | 1581 |
| SciCode | 41.3% | 54.6% |
| LMArena Coding | 1453 | 1439 |
| ALE-Bench | 765.27 | 1,577 |
| DeepSWE | — | 66.6% |
| FrontierCode | — | 42.4% |
| WeirdML | 39% | — |
Agentic & Tool Use GPT-6 Luna leads
Gemini 3.5 Flash Lite: 25.7 (#107), GPT-6 Luna: 33.3 (#54)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6 Luna |
|---|---|---|
| APEX-Agents | 29.3% | 44.3% |
| GDP.pdf | 10% | 23% |
Reasoning GPT-6 Luna leads
Gemini 3.5 Flash Lite: 27.8 (#114), GPT-6 Luna: 48.2 (#41)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6 Luna |
|---|---|---|
| ARC-AGI-2 | 10.3% | 59.3% |
| NYT Connections (extended) | 60.4% | 68.7% |
| ARC-AGI-1 | 53.5% | 86.7% |
| CritPt | 0% | 19.4% |
| Chess Puzzles | 22% | 31% |
| LMArena Hard Prompts | 1441 | 1411 |
| Mystery Game Puzzles | 19% | 7% |
| DTBench | 83.5% | 90.1% |
| LMCA | 37.6% | 44.5% |
| Epoch Capabilities Index | 145.13 | 156.28 |
Math GPT-6 Luna leads
Gemini 3.5 Flash Lite: 25.9 (#264), GPT-6 Luna: 76.1 (#15)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6 Luna |
|---|---|---|
| FrontierMath (Tiers 1-3) | 26% | 78.9% |
| FrontierMath Tier 4 | 0% | 56.1% |
| OTIS Mock AIME 2024-2025 | 71.1% | 98.9% |
| ProofBench | 13% | 64% |
| LMArena Math | 1433 | 1416 |
Knowledge GPT-6 Luna leads
Gemini 3.5 Flash Lite: 50.1 (#72), GPT-6 Luna: 57.0 (#41)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6 Luna |
|---|---|---|
| GPQA Diamond | 83.3% | 90.5% |
| LMArena Expert | 1435 | 1444 |
| SimpleQA Verified | — | 41.4% |
Multimodal GPT-6 Luna leads
Gemini 3.5 Flash Lite: 41.1 (#40), GPT-6 Luna: 42.4 (#30)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6 Luna |
|---|---|---|
| LMArena Vision | 1268 | 1217 |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 44.2% |
Multilingual Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 53.5 (#63), GPT-6 Luna: 50.5 (#117)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | 1427 | 1386 |
| LMArena Chinese | 1469 | 1433 |
| LMArena French | 1451 | 1420 |
| LMArena German | 1454 | 1369 |
| LMArena Japanese | 1427 | 1369 |
| LMArena Korean | 1407 | 1360 |
| LMArena Russian | 1443 | 1394 |
| LMArena Spanish | 1442 | 1393 |
Instruction Following Too close to call
Gemini 3.5 Flash Lite: 74.8 (#85), GPT-6 Luna: 74.3 (#99)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | 1420 | 1409 |
Long Context Too close to call
Gemini 3.5 Flash Lite: 43.9 (#84), GPT-6 Luna: 43.0 (#111)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | 1435 | 1409 |
Writing & Preference Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 64.2 (#57), GPT-6 Luna: 58.3 (#119)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6 Luna |
|---|---|---|
| LMArena Text | 1435 | 1391 |
| LMArena Creative Writing | 1420 | 1363 |
| LMArena Multi-Turn | 1445 | 1396 |
| EQ-Bench Creative Writing | 1559 | — |
Frequently asked questions
Is Gemini 3.5 Flash Lite better than GPT-6 Luna?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 41.5 on the Noometry Index.
Which is cheaper, Gemini 3.5 Flash Lite or GPT-6 Luna?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Gemini 3.5 Flash Lite lists at $0.30 and $2.50.
Is Gemini 3.5 Flash Lite or GPT-6 Luna better for coding?
GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 1.05M.
How many benchmarks do Gemini 3.5 Flash Lite and GPT-6 Luna share?
37 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and GPT-6 Luna has 42.