Model comparison
Gemini 3.6 Flash vs GPT-5.6 Terra
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 54.1 on the Noometry Index. Gemini 3.6 Flash costs 3.0× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Last verified . 45 shared benchmarks.
Summary
- They share 45 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 4 categories and GPT-5.6 Terra in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Terra leads 81.6 to 57.3.
- The biggest single-benchmark swing is FrontierMath Tier 4: 22% for Gemini 3.6 Flash and 70.7% for GPT-5.6 Terra.
- Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 1.05M.
Side by side
| Gemini 3.6 Flash | GPT-5.6 Terra | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 54.1 | 59.2 |
| Released | 2026-07-21 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.75 | $2 |
| Output $ / M tokens | $3.75 | $12 |
| Results tracked | 46 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Terra leads
Gemini 3.6 Flash: 50.0 (#48), GPT-5.6 Terra: 57.7 (#19)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Terra |
|---|---|---|
| DeepSWE | 46.7% | 69.6% |
| FrontierCode | 34.4% | 41.3% |
| LMArena WebDev | 1538 | 1522 |
| SciCode | 52.7% | 55% |
| WeirdML | 56.1% | 78.3% |
| LMArena Coding | 1491 | 1484 |
| ALE-Bench | 715.52 | 1,951 |
| CursorBench | — | 41.3% |
Agentic & Tool Use GPT-5.6 Terra leads
Gemini 3.6 Flash: 32.3 (#65), GPT-5.6 Terra: 40.1 (#25)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Terra |
|---|---|---|
| APEX-Agents | 46.9% | 58.2% |
| GDP.pdf | 14% | 24.7% |
| BALROG | — | 53.2% |
| Vending-Bench 2 | — | 7,343 |
Reasoning GPT-5.6 Terra leads
Gemini 3.6 Flash: 58.8 (#22), GPT-5.6 Terra: 60.7 (#21)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Terra |
|---|---|---|
| ARC-AGI-2 | 60.4% | 83.9% |
| NYT Connections (extended) | 89% | 78.4% |
| ARC-AGI-1 | 91.2% | 96.5% |
| CritPt | 10.6% | 30% |
| Chess Puzzles | 43% | 54% |
| LMArena Hard Prompts | 1485 | 1468 |
| Mystery Game Puzzles | 30% | 35% |
| DTBench | 95.5% | 93.3% |
| LMCA | 44.9% | 55% |
| Epoch Capabilities Index | 154.25 | 159.62 |
| SimpleBench | — | 48.9% |
| Kagi LLM Benchmark | — | 51.3% |
| Surface Evolver Bench | — | 83.8% |
Math GPT-5.6 Terra leads
Gemini 3.6 Flash: 57.3 (#40), GPT-5.6 Terra: 81.6 (#12)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Terra |
|---|---|---|
| FrontierMath (Tiers 1-3) | 58.9% | 86% |
| FrontierMath Tier 4 | 22% | 70.7% |
| OTIS Mock AIME 2024-2025 | 94.2% | 99.7% |
| ProofBench | 36% | 74% |
| LMArena Math | 1505 | 1466 |
| MathArena Final-Answer Competitions | 70.8% | — |
Knowledge Gemini 3.6 Flash leads
Gemini 3.6 Flash: 67.8 (#8), GPT-5.6 Terra: 61.2 (#30)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Terra |
|---|---|---|
| GPQA Diamond | 94.1% | 93.3% |
| SimpleQA Verified | 66.2% | 43.2% |
| LMArena Expert | 1488 | 1492 |
Multimodal GPT-5.6 Terra leads
Gemini 3.6 Flash: 38.5 (#64), GPT-5.6 Terra: 47.3 (#11)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Terra |
|---|---|---|
| LMArena Vision | 1298 | 1271 |
| Blueprint-Bench 2 | 31.2% | 30.8% |
| Furniture Assembly | 23.3% | 54.2% |
| LMArena Document | 1456 | 1472 |
Multilingual Gemini 3.6 Flash leads
Gemini 3.6 Flash: 56.5 (#19), GPT-5.6 Terra: 54.4 (#44)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Terra |
|---|---|---|
| LMArena Non-English | 1469 | 1439 |
| LMArena Chinese | 1531 | 1513 |
| LMArena French | 1504 | 1471 |
| LMArena German | 1478 | 1460 |
| LMArena Japanese | 1476 | 1457 |
| LMArena Korean | 1431 | 1425 |
| LMArena Russian | 1487 | 1450 |
| LMArena Spanish | 1475 | 1448 |
Instruction Following Too close to call
Gemini 3.6 Flash: 77.0 (#33), GPT-5.6 Terra: 76.4 (#40)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Terra |
|---|---|---|
| LMArena Instruction Following | 1466 | 1454 |
Long Context Too close to call
Gemini 3.6 Flash: 45.1 (#50), GPT-5.6 Terra: 44.4 (#68)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Terra |
|---|---|---|
| LMArena Longer Query | 1474 | 1451 |
Writing & Preference GPT-5.6 Terra leads
Gemini 3.6 Flash: 68.2 (#27), GPT-5.6 Terra: 70.2 (#23)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Terra |
|---|---|---|
| LMArena Text | 1479 | 1447 |
| LMArena Creative Writing | 1465 | 1410 |
| EQ-Bench Creative Writing | 1604 | 1855 |
| LMArena Multi-Turn | 1481 | 1449 |
| EQ-Bench 4 | — | 1234 |
Frequently asked questions
Is Gemini 3.6 Flash better than GPT-5.6 Terra?
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 54.1 on the Noometry Index. Gemini 3.6 Flash costs 3.0× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.6 Flash or GPT-5.6 Terra?
Gemini 3.6 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GPT-5.6 Terra lists at $2 and $12.
Is Gemini 3.6 Flash or GPT-5.6 Terra better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 50.0 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 1.05M.
How many benchmarks do Gemini 3.6 Flash and GPT-5.6 Terra share?
45 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and GPT-5.6 Terra has 52.