Model comparison
Gemini 3.7 Flash vs GPT-5.6 Luna
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 54.6 on the Noometry Index. GPT-5.6 Luna costs 3.3× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.
Last verified . 42 shared benchmarks.
GoogleSummary
- They share 42 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 8 categories and GPT-5.6 Luna in 2 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.0 to 47.6.
- The biggest single-benchmark swing is SimpleQA Verified: 69.2% for Gemini 3.7 Flash and 41% for GPT-5.6 Luna.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.7 Flash.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 1.05M.
Side by side
| Gemini 3.7 Flash | GPT-5.6 Luna | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 59.8 | 54.6 |
| Released | 2026-08-13 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.75 | $0.20 |
| Output $ / M tokens | $3.75 | $1.20 |
| Results tracked | 44 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.7 Flash leads
Gemini 3.7 Flash: 56.2 (#22), GPT-5.6 Luna: 54.5 (#28)
| Benchmark | Gemini 3.7 Flash | GPT-5.6 Luna |
|---|---|---|
| DeepSWE | 65.5% | 67.2% |
| FrontierCode | 43.6% | 39.8% |
| LMArena WebDev | 1592 | 1519 |
| SciCode | 59.8% | 53.6% |
| LMArena Coding | 1497 | 1466 |
| ALE-Bench | 904.3 | 1,667 |
| CursorBench | — | 35.9% |
| FrontierSWE | 20.3% | — |
| WeirdML | — | 60.9% |
Agentic & Tool Use Gemini 3.7 Flash leads
Gemini 3.7 Flash: 42.1 (#19), GPT-5.6 Luna: 34.4 (#45)
| Benchmark | Gemini 3.7 Flash | GPT-5.6 Luna |
|---|---|---|
| APEX-Agents | 67.8% | 43% |
| GDP.pdf | 23.8% | 22.7% |
| Remote Labor Index | 5% | — |
| BALROG | — | 45.6% |
| Vending-Bench 2 | — | 4,095 |
Reasoning Gemini 3.7 Flash leads
Gemini 3.7 Flash: 70.0 (#15), GPT-5.6 Luna: 47.6 (#43)
| Benchmark | Gemini 3.7 Flash | GPT-5.6 Luna |
|---|---|---|
| ARC-AGI-2 | 84.6% | 59.5% |
| NYT Connections (extended) | 94% | 69.4% |
| ARC-AGI-1 | 95.5% | 88% |
| CritPt | 14.3% | 20.6% |
| Chess Puzzles | 47% | 40% |
| LMArena Hard Prompts | 1494 | 1451 |
| Mystery Game Puzzles | 37% | 21% |
| DTBench | 96.8% | 89.1% |
| LMCA | 50.4% | 48.5% |
| Epoch Capabilities Index | 157.27 | 156.39 |
| SimpleBench | — | 46.8% |
| Kagi LLM Benchmark | — | 49.1% |
| Surface Evolver Bench | — | 61.9% |
Math GPT-5.6 Luna leads
Gemini 3.7 Flash: 69.6 (#23), GPT-5.6 Luna: 77.7 (#14)
| Benchmark | Gemini 3.7 Flash | GPT-5.6 Luna |
|---|---|---|
| FrontierMath (Tiers 1-3) | 71.6% | 82.1% |
| FrontierMath Tier 4 | 36.6% | 61% |
| OTIS Mock AIME 2024-2025 | 97.2% | 98.3% |
| ProofBench | 58% | 60% |
| LMArena Math | 1507 | 1458 |
Knowledge Gemini 3.7 Flash leads
Gemini 3.7 Flash: 69.7 (#5), GPT-5.6 Luna: 58.5 (#34)
| Benchmark | Gemini 3.7 Flash | GPT-5.6 Luna |
|---|---|---|
| GPQA Diamond | 94.8% | 91.6% |
| SimpleQA Verified | 69.2% | 41% |
| LMArena Expert | 1508 | 1478 |
Multimodal GPT-5.6 Luna leads
Gemini 3.7 Flash: 37.3 (#73), GPT-5.6 Luna: 42.7 (#28)
| Benchmark | Gemini 3.7 Flash | GPT-5.6 Luna |
|---|---|---|
| LMArena Vision | 1316 | 1258 |
| Furniture Assembly | 26.7% | 42.5% |
| Blueprint-Bench 2 | — | 22.6% |
| LMArena Document | — | 1457 |
Multilingual Gemini 3.7 Flash leads
Gemini 3.7 Flash: 57.6 (#7), GPT-5.6 Luna: 52.8 (#78)
| Benchmark | Gemini 3.7 Flash | GPT-5.6 Luna |
|---|---|---|
| LMArena Non-English | 1484 | 1417 |
| LMArena Chinese | 1548 | 1470 |
| LMArena French | 1505 | 1456 |
| LMArena German | 1498 | 1454 |
| LMArena Japanese | 1512 | 1411 |
| LMArena Korean | 1483 | 1415 |
| LMArena Russian | 1516 | 1428 |
| LMArena Spanish | 1503 | 1448 |
Instruction Following Gemini 3.7 Flash leads
Gemini 3.7 Flash: 77.7 (#15), GPT-5.6 Luna: 75.6 (#57)
| Benchmark | Gemini 3.7 Flash | GPT-5.6 Luna |
|---|---|---|
| LMArena Instruction Following | 1483 | 1437 |
Long Context Gemini 3.7 Flash leads
Gemini 3.7 Flash: 45.7 (#30), GPT-5.6 Luna: 43.9 (#82)
| Benchmark | Gemini 3.7 Flash | GPT-5.6 Luna |
|---|---|---|
| LMArena Longer Query | 1492 | 1436 |
Writing & Preference Gemini 3.7 Flash leads
Gemini 3.7 Flash: 71.2 (#20), GPT-5.6 Luna: 68.0 (#29)
| Benchmark | Gemini 3.7 Flash | GPT-5.6 Luna |
|---|---|---|
| LMArena Text | 1486 | 1431 |
| LMArena Creative Writing | 1490 | 1396 |
| EQ-Bench Creative Writing | 1723 | 1829 |
| LMArena Multi-Turn | 1489 | 1434 |
| EQ-Bench 4 | — | 1156 |
Frequently asked questions
Is Gemini 3.7 Flash better than GPT-5.6 Luna?
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 54.6 on the Noometry Index. GPT-5.6 Luna costs 3.3× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.7 Flash 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 3.7 Flash lists at $0.75 and $3.75.
Is Gemini 3.7 Flash or GPT-5.6 Luna better for coding?
Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 54.5 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 3.7 Flash and GPT-5.6 Luna share?
42 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and GPT-5.6 Luna has 52.