Model comparison
Gemini 3.6 Flash vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 54.1 on the Noometry Index. Gemini 3.6 Flash costs 2.7× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 42 shared benchmarks.
GoogleSummary
- They share 42 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 4 categories and GPT-6 Sol in 6 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 57.3.
- The biggest single-benchmark swing is FrontierMath Tier 4: 22% for Gemini 3.6 Flash and 90% for GPT-6 Sol.
- Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 1.05M.
Side by side
| Gemini 3.6 Flash | GPT-6 Sol | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 54.1 | 61.8 |
| Released | 2026-07-21 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.75 | $2 |
| Output $ / M tokens | $3.75 | $10 |
| Results tracked | 46 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Gemini 3.6 Flash: 50.0 (#48), GPT-6 Sol: 60.1 (#11)
| Benchmark | Gemini 3.6 Flash | GPT-6 Sol |
|---|---|---|
| DeepSWE | 46.7% | 68.8% |
| FrontierCode | 34.4% | 49.3% |
| LMArena WebDev | 1538 | 1688 |
| SciCode | 52.7% | 57.6% |
| LMArena Coding | 1491 | 1447 |
| ALE-Bench | 715.52 | 2,462 |
| WeirdML | 56.1% | — |
Agentic & Tool Use GPT-6 Sol leads
Gemini 3.6 Flash: 32.3 (#65), GPT-6 Sol: 37.2 (#36)
| Benchmark | Gemini 3.6 Flash | GPT-6 Sol |
|---|---|---|
| APEX-Agents | 46.9% | 54.3% |
| GDP.pdf | 14% | 26.4% |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
Gemini 3.6 Flash: 58.8 (#22), GPT-6 Sol: 74.0 (#9)
| Benchmark | Gemini 3.6 Flash | GPT-6 Sol |
|---|---|---|
| ARC-AGI-2 | 60.4% | 89.6% |
| NYT Connections (extended) | 89% | 90.1% |
| ARC-AGI-1 | 91.2% | 95.5% |
| CritPt | 10.6% | 30.9% |
| LMArena Hard Prompts | 1485 | 1418 |
| Mystery Game Puzzles | 30% | 56% |
| DTBench | 95.5% | 97.3% |
| LMCA | 44.9% | 59.1% |
| Epoch Capabilities Index | 154.25 | 162.72 |
| Chess Puzzles | 43% | — |
| EBR-Bench | — | 53.3% |
Math GPT-6 Sol leads
Gemini 3.6 Flash: 57.3 (#40), GPT-6 Sol: 87.2 (#7)
| Benchmark | Gemini 3.6 Flash | GPT-6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 58.9% | 89.8% |
| FrontierMath Tier 4 | 22% | 90% |
| OTIS Mock AIME 2024-2025 | 94.2% | 100% |
| ProofBench | 36% | 83% |
| LMArena Math | 1505 | 1402 |
| MathArena Final-Answer Competitions | 70.8% | — |
Knowledge Gemini 3.6 Flash leads
Gemini 3.6 Flash: 67.8 (#8), GPT-6 Sol: 64.8 (#15)
| Benchmark | Gemini 3.6 Flash | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 94.1% | 94.3% |
| SimpleQA Verified | 66.2% | 60.7% |
| LMArena Expert | 1488 | 1439 |
| Vectara Hallucination Rate | — | 6.5% |
Multimodal GPT-6 Sol leads
Gemini 3.6 Flash: 38.5 (#64), GPT-6 Sol: 47.6 (#10)
| Benchmark | Gemini 3.6 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1298 | 1245 |
| Blueprint-Bench 2 | 31.2% | 36.9% |
| Furniture Assembly | 23.3% | 58.3% |
| LMArena Document | 1456 | — |
Multilingual Gemini 3.6 Flash leads
Gemini 3.6 Flash: 56.5 (#19), GPT-6 Sol: 50.5 (#118)
| Benchmark | Gemini 3.6 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1469 | 1385 |
| LMArena Chinese | 1531 | 1405 |
| LMArena French | 1504 | 1410 |
| LMArena German | 1478 | 1390 |
| LMArena Japanese | 1476 | 1385 |
| LMArena Korean | 1431 | 1341 |
| LMArena Russian | 1487 | 1401 |
| LMArena Spanish | 1475 | 1384 |
Instruction Following Gemini 3.6 Flash leads
Gemini 3.6 Flash: 77.0 (#33), GPT-6 Sol: 74.5 (#94)
| Benchmark | Gemini 3.6 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1466 | 1412 |
Long Context Gemini 3.6 Flash leads
Gemini 3.6 Flash: 45.1 (#50), GPT-6 Sol: 43.1 (#108)
| Benchmark | Gemini 3.6 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1474 | 1411 |
Writing & Preference GPT-6 Sol leads
Gemini 3.6 Flash: 68.2 (#27), GPT-6 Sol: 71.9 (#18)
| Benchmark | Gemini 3.6 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1479 | 1395 |
| LMArena Creative Writing | 1465 | 1378 |
| EQ-Bench Creative Writing | 1604 | 2125 |
| LMArena Multi-Turn | 1481 | 1412 |
Frequently asked questions
Is Gemini 3.6 Flash better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 54.1 on the Noometry Index. Gemini 3.6 Flash costs 2.7× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.6 Flash or GPT-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-6 Sol lists at $2 and $10.
Is Gemini 3.6 Flash or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 50.0 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 1.05M.
How many benchmarks do Gemini 3.6 Flash and GPT-6 Sol share?
42 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and GPT-6 Sol has 45.