Model comparison
Gemini 3 Flash Preview vs GPT-5.2
GPT-5.2 is the stronger model overall, scoring 54.1 to 52.3 on the Noometry Index. Gemini 3 Flash Preview costs 4.3× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.
Last verified . 55 shared benchmarks.
GoogleSummary
- They share 55 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 3 categories and GPT-5.2 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.2 leads 60.0 to 51.7.
- The biggest single-benchmark swing is SimpleQA Verified: 66.8% for Gemini 3 Flash Preview and 37.1% for GPT-5.2.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 400K.
Side by side
| Gemini 3 Flash Preview | GPT-5.2 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 52.3 | 54.1 |
| Released | 2025-12-17 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.50 | $1.75 |
| Output $ / M tokens | $3 | $14 |
| Results tracked | 59 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 3 Flash Preview: 50.9 (#42), GPT-5.2: 51.6 (#37)
| Benchmark | Gemini 3 Flash Preview | GPT-5.2 |
|---|---|---|
| SWE-bench Verified | 75.4% | 73.8% |
| SWE-bench Verified (bash only) | 75.8% | 72.8% |
| LMArena WebDev | 1439 | 1416 |
| SWE-bench Multilingual | 72.7% | 66.7% |
| GSO | 9.8% | 27.4% |
| WeirdML | 61.6% | 72.2% |
| LMArena Coding | 1460 | 1447 |
| ALE-Bench | 1,367 | 1,294 |
| AlgoTune | — | 2.05 |
Agentic & Tool Use GPT-5.2 leads
Gemini 3 Flash Preview: 38.7 (#29), GPT-5.2: 40.2 (#24)
| Benchmark | Gemini 3 Flash Preview | GPT-5.2 |
|---|---|---|
| Terminal-Bench | 64.3% | 64.9% |
| τ²-bench Airline | 82.5% | 83% |
| τ²-bench Banking | 27.3% | 32.2% |
| τ²-bench Retail | 76.8% | 81.6% |
| τ²-bench Telecom | 91.2% | 89.7% |
| DeepResearch Bench | 49.8% | 41.1% |
| LMArena Search | 1198 | 1207 |
| Vending-Bench 2 | 3,635 | 3,591 |
| Berkeley Function Calling Leaderboard | — | 55.9% |
| GDPval | — | 49.7% |
| Remote Labor Index | — | 2.5% |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |
| METR Time Horizons | — | 75.3% |
Reasoning GPT-5.2 leads
Gemini 3 Flash Preview: 49.2 (#37), GPT-5.2: 50.2 (#35)
| Benchmark | Gemini 3 Flash Preview | GPT-5.2 |
|---|---|---|
| ARC-AGI-2 | 33.6% | 52.9% |
| SimpleBench | 61.1% | 45.8% |
| NYT Connections (extended) | 83.1% | 83.6% |
| ARC-AGI-1 | 84.7% | 86.2% |
| Chess Puzzles | 40% | 49% |
| LMArena Hard Prompts | 1465 | 1445 |
| Mystery Game Puzzles | 26% | 23% |
| DTBench | 89.1% | 90.9% |
| LMCA | 43.1% | 43.9% |
| Epoch Capabilities Index | 151.8 | 153.45 |
| ForecastBench | 58.5 | 60.1 |
| Kagi LLM Benchmark | — | 73.3% |
| EnigmaEval | — | 10.4% |
| EBR-Bench | — | 23% |
Math GPT-5.2 leads
Gemini 3 Flash Preview: 51.7 (#55), GPT-5.2: 60.0 (#38)
| Benchmark | Gemini 3 Flash Preview | GPT-5.2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 67.4% |
| FrontierMath Tier 4 | 17.1% | 31.7% |
| MathArena Final-Answer Competitions | 67.6% | 72% |
| OTIS Mock AIME 2024-2025 | 95.6% | 96.1% |
| ProofBench | 15% | 15% |
| LMArena Math | 1473 | 1440 |
| FrontierMath (Feb 2025 set) | 35.6% | 40.7% |
| FrontierMath Tier 4 (v1) | 4.2% | 18.8% |
Knowledge Too close to call
Gemini 3 Flash Preview: 58.8 (#33), GPT-5.2: 59.3 (#32)
| Benchmark | Gemini 3 Flash Preview | GPT-5.2 |
|---|---|---|
| GPQA Diamond | 89.4% | 91.4% |
| SimpleQA Verified | 66.8% | 37.1% |
| Vectara Hallucination Rate | 13.5% | 8.4% |
| LMArena Expert | 1462 | 1445 |
| Humanity's Last Exam | — | 27.8% |
Multimodal GPT-5.2 leads
Gemini 3 Flash Preview: 45.5 (#16), GPT-5.2: 51.3 (#7)
| Benchmark | Gemini 3 Flash Preview | GPT-5.2 |
|---|---|---|
| LMArena Vision | 1285 | 1268 |
| VPCT | 72.6% | 84% |
| LMArena Document | 1413 | 1405 |
| GeoBench | 88% | — |
| Blueprint-Bench 2 | 0% | — |
| Furniture Assembly | — | 38.3% |
Multilingual Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 55.7 (#27), GPT-5.2: 53.4 (#67)
| Benchmark | Gemini 3 Flash Preview | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1458 | 1425 |
| LMArena Chinese | 1511 | 1460 |
| LMArena French | 1477 | 1455 |
| LMArena German | 1497 | 1448 |
| LMArena Japanese | 1489 | 1420 |
| LMArena Korean | 1443 | 1392 |
| LMArena Russian | 1480 | 1440 |
| LMArena Spanish | 1469 | 1433 |
Instruction Following Too close to call
Gemini 3 Flash Preview: 75.7 (#56), GPT-5.2: 74.7 (#89)
| Benchmark | Gemini 3 Flash Preview | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1437 | 1417 |
Long Context Too close to call
Gemini 3 Flash Preview: 44.4 (#67), GPT-5.2: 44.0 (#78)
| Benchmark | Gemini 3 Flash Preview | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1452 | 1428 |
| CL-bench | — | 18.2% |
Writing & Preference GPT-5.2 leads
Gemini 3 Flash Preview: 65.5 (#45), GPT-5.2: 66.8 (#32)
| Benchmark | Gemini 3 Flash Preview | GPT-5.2 |
|---|---|---|
| LMArena Text | 1466 | 1439 |
| LMArena Creative Writing | 1457 | 1401 |
| LMArena Multi-Turn | 1471 | 1458 |
| EQ-Bench Creative Writing | — | 1703 |
Frequently asked questions
Is Gemini 3 Flash Preview better than GPT-5.2?
GPT-5.2 is the stronger model overall, scoring 54.1 to 52.3 on the Noometry Index. Gemini 3 Flash Preview costs 4.3× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.
Which is cheaper, Gemini 3 Flash Preview or GPT-5.2?
Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; GPT-5.2 lists at $1.75 and $14.
Is Gemini 3 Flash Preview or GPT-5.2 better for coding?
They score almost the same on coding (50.9 vs 51.6); test both on your own repository before choosing.
Which has the bigger context window?
Gemini 3 Flash Preview does, with 1.05M tokens against 400K.
How many benchmarks do Gemini 3 Flash Preview and GPT-5.2 share?
55 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and GPT-5.2 has 67.