Model comparison
Gemini 3 Flash Preview vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 52.3 on the Noometry Index. Gemini 3 Flash Preview costs 3.6× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 37 shared benchmarks.
GoogleSummary
- They share 37 benchmarks with published results for both. Gemini 3 Flash Preview 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 51.7.
- The biggest single-benchmark swing is FrontierMath Tier 4: 17.1% for Gemini 3 Flash Preview and 90% for GPT-6 Sol.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 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 Flash Preview | GPT-6 Sol | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 52.3 | 61.8 |
| Released | 2025-12-17 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.50 | $2 |
| Output $ / M tokens | $3 | $10 |
| Results tracked | 59 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Gemini 3 Flash Preview: 50.9 (#42), GPT-6 Sol: 60.1 (#11)
| Benchmark | Gemini 3 Flash Preview | GPT-6 Sol |
|---|---|---|
| LMArena WebDev | 1439 | 1688 |
| LMArena Coding | 1460 | 1447 |
| ALE-Bench | 1,367 | 2,462 |
| SWE-bench Verified | 75.4% | — |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| SWE-bench Verified (bash only) | 75.8% | — |
| SWE-bench Multilingual | 72.7% | — |
| SciCode | — | 57.6% |
| GSO | 9.8% | — |
| WeirdML | 61.6% | — |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 38.7 (#29), GPT-6 Sol: 37.2 (#36)
| Benchmark | Gemini 3 Flash Preview | GPT-6 Sol |
|---|---|---|
| GDP.pdf | 10% | 26.4% |
| Vending-Bench 2 | 3,635 | 14,428 |
| Terminal-Bench | 64.3% | — |
| APEX-Agents | — | 54.3% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| LMArena Search | 1198 | — |
Reasoning GPT-6 Sol leads
Gemini 3 Flash Preview: 49.2 (#37), GPT-6 Sol: 74.0 (#9)
| Benchmark | Gemini 3 Flash Preview | GPT-6 Sol |
|---|---|---|
| ARC-AGI-2 | 33.6% | 89.6% |
| NYT Connections (extended) | 83.1% | 90.1% |
| ARC-AGI-1 | 84.7% | 95.5% |
| LMArena Hard Prompts | 1465 | 1418 |
| Mystery Game Puzzles | 26% | 56% |
| DTBench | 89.1% | 97.3% |
| LMCA | 43.1% | 59.1% |
| Epoch Capabilities Index | 151.8 | 162.72 |
| SimpleBench | 61.1% | — |
| CritPt | — | 30.9% |
| Chess Puzzles | 40% | — |
| EBR-Bench | — | 53.3% |
| ForecastBench | 58.5 | — |
Math GPT-6 Sol leads
Gemini 3 Flash Preview: 51.7 (#55), GPT-6 Sol: 87.2 (#7)
| Benchmark | Gemini 3 Flash Preview | GPT-6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 89.8% |
| FrontierMath Tier 4 | 17.1% | 90% |
| OTIS Mock AIME 2024-2025 | 95.6% | 100% |
| ProofBench | 15% | 83% |
| LMArena Math | 1473 | 1402 |
| MathArena Final-Answer Competitions | 67.6% | — |
| FrontierMath (Feb 2025 set) | 35.6% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge GPT-6 Sol leads
Gemini 3 Flash Preview: 58.8 (#33), GPT-6 Sol: 64.8 (#15)
| Benchmark | Gemini 3 Flash Preview | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 89.4% | 94.3% |
| SimpleQA Verified | 66.8% | 60.7% |
| Vectara Hallucination Rate | 13.5% | 6.5% |
| LMArena Expert | 1462 | 1439 |
Multimodal GPT-6 Sol leads
Gemini 3 Flash Preview: 45.5 (#16), GPT-6 Sol: 47.6 (#10)
| Benchmark | Gemini 3 Flash Preview | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1285 | 1245 |
| Blueprint-Bench 2 | 0% | 36.9% |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Furniture Assembly | — | 58.3% |
| LMArena Document | 1413 | — |
Multilingual Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 55.7 (#27), GPT-6 Sol: 50.5 (#118)
| Benchmark | Gemini 3 Flash Preview | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1458 | 1385 |
| LMArena Chinese | 1511 | 1405 |
| LMArena French | 1477 | 1410 |
| LMArena German | 1497 | 1390 |
| LMArena Japanese | 1489 | 1385 |
| LMArena Korean | 1443 | 1341 |
| LMArena Russian | 1480 | 1401 |
| LMArena Spanish | 1469 | 1384 |
Instruction Following Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 75.7 (#56), GPT-6 Sol: 74.5 (#94)
| Benchmark | Gemini 3 Flash Preview | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1437 | 1412 |
Long Context Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 44.4 (#67), GPT-6 Sol: 43.1 (#108)
| Benchmark | Gemini 3 Flash Preview | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1452 | 1411 |
Writing & Preference GPT-6 Sol leads
Gemini 3 Flash Preview: 65.5 (#45), GPT-6 Sol: 71.9 (#18)
| Benchmark | Gemini 3 Flash Preview | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1466 | 1395 |
| LMArena Creative Writing | 1457 | 1378 |
| LMArena Multi-Turn | 1471 | 1412 |
| EQ-Bench Creative Writing | — | 2125 |
Frequently asked questions
Is Gemini 3 Flash Preview better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 52.3 on the Noometry Index. Gemini 3 Flash Preview costs 3.6× 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 Flash Preview or GPT-6 Sol?
Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is Gemini 3 Flash Preview or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 50.9 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 Flash Preview and GPT-6 Sol share?
37 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and GPT-6 Sol has 45.