Model comparison
Gemini 3.6 Flash vs GPT-5.6 Sol
GPT-5.6 Sol is the stronger model overall, scoring 64.4 to 54.1 on the Noometry Index. Gemini 3.6 Flash costs 5.3× less per token, which makes it the better buy when GPT-5.6 Sol's lead doesn't matter for your workload.
Last verified . 45 shared benchmarks.
GoogleSummary
- They share 45 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 2 categories and GPT-5.6 Sol in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Sol leads 85.5 to 57.0.
- The biggest single-benchmark swing is FrontierMath Tier 4: 22% for Gemini 3.6 Flash and 82.9% for GPT-5.6 Sol.
- Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $4 / $20 for GPT-5.6 Sol.
- GPT-5.6 Sol accepts more context: 1.05M tokens versus 1.05M.
Side by side
| Gemini 3.6 Flash | GPT-5.6 Sol | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 54.1 | 64.4 |
| 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 | $4 |
| Output $ / M tokens | $3.75 | $20 |
| Results tracked | 46 | 64 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Sol leads
Gemini 3.6 Flash: 49.6 (#45), GPT-5.6 Sol: 61.1 (#7)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Sol |
|---|---|---|
| DeepSWE | 46.7% | 72.7% |
| FrontierCode | 34.4% | 47.5% |
| LMArena WebDev | 1536 | 1619 |
| SciCode | 52.7% | 57.1% |
| WeirdML | 56.1% | 89.4% |
| LMArena Coding | 1492 | 1493 |
| ALE-Bench | 715.52 | 2,177 |
| CursorBench | — | 41.7% |
| FrontierSWE | — | 32.2% |
| MirrorCode | — | 20% |
Agentic & Tool Use GPT-5.6 Sol leads
Gemini 3.6 Flash: 32.4 (#56), GPT-5.6 Sol: 50.2 (#7)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Sol |
|---|---|---|
| APEX-Agents | 46.9% | 51.4% |
| GDP.pdf | 14% | 30.7% |
| OSWorld 2.0 | — | 27.3% |
| τ²-bench Banking | — | 46.9% |
| PostTrainBench | — | 36.2% |
| BALROG | — | 60% |
| GBAEval | — | 52.6% |
| LMArena Search | — | 1257 |
| Vending-Bench 2 | — | 9,619 |
Reasoning GPT-5.6 Sol leads
Gemini 3.6 Flash: 58.9 (#20), GPT-5.6 Sol: 74.7 (#6)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Sol |
|---|---|---|
| ARC-AGI-2 | 60.4% | 92.5% |
| NYT Connections (extended) | 89% | 93.8% |
| ARC-AGI-1 | 91.2% | 97.5% |
| CritPt | 10.6% | 32.3% |
| Chess Puzzles | 43% | 64% |
| LMArena Hard Prompts | 1486 | 1481 |
| Mystery Game Puzzles | 30% | 58% |
| DTBench | 95.5% | 96% |
| LMCA | 44.9% | 59.2% |
| Epoch Capabilities Index | 154.36 | 161.99 |
| SimpleBench | — | 71.7% |
| Kagi LLM Benchmark | — | 67% |
| EnigmaEval | — | 37.1% |
| EBR-Bench | — | 44.8% |
| Surface Evolver Bench | — | 93.1% |
| Bench to the Future 3 | — | 0.14 |
Math GPT-5.6 Sol leads
Gemini 3.6 Flash: 57.0 (#33), GPT-5.6 Sol: 85.5 (#7)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 58.9% | 89.1% |
| FrontierMath Tier 4 | 22% | 82.9% |
| OTIS Mock AIME 2024-2025 | 94.2% | 100% |
| ProofBench | 36% | 83% |
| LMArena Math | 1504 | 1472 |
| MathArena Final-Answer Competitions | 70.8% | — |
| FrontierMath Erdős | — | 0% |
Knowledge Gemini 3.6 Flash leads
Gemini 3.6 Flash: 67.8 (#7), GPT-5.6 Sol: 64.3 (#16)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Sol |
|---|---|---|
| GPQA Diamond | 94.1% | 93.5% |
| SimpleQA Verified | 66.2% | 69.7% |
| LMArena Expert | 1489 | 1517 |
| Vectara Hallucination Rate | — | 12.4% |
Multimodal GPT-5.6 Sol leads
Gemini 3.6 Flash: 38.7 (#55), GPT-5.6 Sol: 48.9 (#8)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Sol |
|---|---|---|
| LMArena Vision | 1297 | 1281 |
| Blueprint-Bench 2 | 31.2% | 33.6% |
| Furniture Assembly | 23.3% | 56.7% |
| LMArena Document | 1456 | 1483 |
Multilingual Gemini 3.6 Flash leads
Gemini 3.6 Flash: 56.8 (#17), GPT-5.6 Sol: 55.4 (#32)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Sol |
|---|---|---|
| LMArena Non-English | 1470 | 1450 |
| LMArena Chinese | 1530 | 1523 |
| LMArena French | 1501 | 1475 |
| LMArena German | 1478 | 1476 |
| LMArena Japanese | 1477 | 1475 |
| LMArena Korean | 1435 | 1434 |
| LMArena Russian | 1490 | 1466 |
| LMArena Spanish | 1477 | 1449 |
Instruction Following Too close to call
Gemini 3.6 Flash: 77.2 (#27), GPT-5.6 Sol: 77.8 (#16)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Sol |
|---|---|---|
| LMArena Instruction Following | 1467 | 1480 |
Long Context Too close to call
Gemini 3.6 Flash: 45.1 (#47), GPT-5.6 Sol: 45.3 (#42)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Sol |
|---|---|---|
| LMArena Longer Query | 1475 | 1479 |
Writing & Preference GPT-5.6 Sol leads
Gemini 3.6 Flash: 68.3 (#26), GPT-5.6 Sol: 73.5 (#12)
| Benchmark | Gemini 3.6 Flash | GPT-5.6 Sol |
|---|---|---|
| LMArena Text | 1478 | 1456 |
| LMArena Creative Writing | 1464 | 1450 |
| EQ-Bench Creative Writing | 1604 | 1972 |
| LMArena Multi-Turn | 1481 | 1456 |
| EQ-Bench 4 | — | 1250 |
Frequently asked questions
Is Gemini 3.6 Flash better than GPT-5.6 Sol?
GPT-5.6 Sol is the stronger model overall, scoring 64.4 to 54.1 on the Noometry Index. Gemini 3.6 Flash costs 5.3× less per token, which makes it the better buy when GPT-5.6 Sol's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.6 Flash or GPT-5.6 Sol?
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 Sol lists at $4 and $20.
Is Gemini 3.6 Flash or GPT-5.6 Sol better for coding?
GPT-5.6 Sol scores higher on coding benchmarks: 61.1 versus 49.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Sol does, with 1.05M tokens against 1.05M.
How many benchmarks do Gemini 3.6 Flash and GPT-5.6 Sol share?
45 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and GPT-5.6 Sol has 64.