Model comparison
Gemini 3 Flash Preview vs GPT-4.1
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 35.9 on the Noometry Index.
Last verified . 38 shared benchmarks.
GoogleSummary
- They share 38 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 10 categories and GPT-4.1 in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 11.7.
- The biggest single-benchmark swing is ARC-AGI-1: 84.7% for Gemini 3 Flash Preview and 5.5% for GPT-4.1.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $2 / $8 for GPT-4.1.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 1.05M.
Side by side
| Gemini 3 Flash Preview | GPT-4.1 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 52.3 | 35.9 |
| Released | 2025-12-17 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 33K |
| Input $ / M tokens | $0.50 | $2 |
| Output $ / M tokens | $3 | $8 |
| Results tracked | 59 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 50.9 (#42), GPT-4.1: 34.4 (#238)
| Benchmark | Gemini 3 Flash Preview | GPT-4.1 |
|---|---|---|
| SWE-bench Verified | 75.4% | 48.5% |
| SWE-bench Verified (bash only) | 75.8% | 39.6% |
| WeirdML | 61.6% | 39% |
| LMArena Coding | 1460 | 1391 |
| ALE-Bench | 1,367 | 558.1 |
| Aider Polyglot | — | 52.4% |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 72.7% | — |
| GSO | 9.8% | — |
| CadEval | — | 42% |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 38.7 (#29), GPT-4.1: 34.7 (#43)
| Benchmark | Gemini 3 Flash Preview | GPT-4.1 |
|---|---|---|
| Terminal-Bench | 64.3% | — |
| Berkeley Function Calling Leaderboard | — | 54% |
| 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% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
| Vending-Bench 2 | 3,635 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), GPT-4.1: 11.7 (#339)
| Benchmark | Gemini 3 Flash Preview | GPT-4.1 |
|---|---|---|
| ARC-AGI-2 | 33.6% | 0.4% |
| SimpleBench | 61.1% | 27% |
| ARC-AGI-1 | 84.7% | 5.5% |
| Chess Puzzles | 40% | 6% |
| LMArena Hard Prompts | 1465 | 1384 |
| DTBench | 89.1% | 68.3% |
| LMCA | 43.1% | 25.6% |
| Epoch Capabilities Index | 151.8 | 136.78 |
| ForecastBench | 58.5 | 61.5 |
| Kagi LLM Benchmark | — | 52.3% |
| NYT Connections (extended) | 83.1% | — |
| EnigmaEval | — | 2.2% |
| Mystery Game Puzzles | 26% | — |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.7 (#55), GPT-4.1: 22.3 (#280)
| Benchmark | Gemini 3 Flash Preview | GPT-4.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 6% |
| OTIS Mock AIME 2024-2025 | 95.6% | 38.3% |
| LMArena Math | 1473 | 1370 |
| FrontierMath (Feb 2025 set) | 35.6% | 5.5% |
| FrontierMath Tier 4 (v1) | 4.2% | 0% |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 15% | — |
| Omni-MATH | — | 47.1% |
| MATH Level 5 | — | 83% |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), GPT-4.1: 37.1 (#160)
| Benchmark | Gemini 3 Flash Preview | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 89.4% | 66.9% |
| SimpleQA Verified | 66.8% | 31.1% |
| Vectara Hallucination Rate | 13.5% | 5.6% |
| LMArena Expert | 1462 | 1364 |
| Humanity's Last Exam | — | 5.4% |
| MMLU-Pro | — | 81.1% |
| GPQA (HELM) | — | 65.9% |
Multimodal Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 45.5 (#16), GPT-4.1: 38.2 (#67)
| Benchmark | Gemini 3 Flash Preview | GPT-4.1 |
|---|---|---|
| LMArena Vision | 1285 | 1211 |
| GeoBench | 88% | 72% |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |
Multilingual Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 55.7 (#27), GPT-4.1: 49.4 (#133)
| Benchmark | Gemini 3 Flash Preview | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1458 | 1370 |
| LMArena Chinese | 1511 | 1382 |
| LMArena French | 1477 | 1382 |
| LMArena German | 1497 | 1381 |
| LMArena Japanese | 1489 | 1319 |
| LMArena Korean | 1443 | 1339 |
| LMArena Russian | 1480 | 1377 |
| LMArena Spanish | 1469 | 1376 |
Instruction Following Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 75.7 (#56), GPT-4.1: 71.3 (#153)
| Benchmark | Gemini 3 Flash Preview | GPT-4.1 |
|---|---|---|
| LMArena Instruction Following | 1437 | 1367 |
| IFEval | — | 83.8% |
Long Context Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 44.4 (#67), GPT-4.1: 40.0 (#163)
| Benchmark | Gemini 3 Flash Preview | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1452 | 1385 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 65.5 (#45), GPT-4.1: 57.6 (#125)
| Benchmark | Gemini 3 Flash Preview | GPT-4.1 |
|---|---|---|
| LMArena Text | 1466 | 1383 |
| LMArena Creative Writing | 1457 | 1363 |
| LMArena Multi-Turn | 1471 | 1398 |
| EQ-Bench Creative Writing | — | 1420 |
| WildBench | — | 85.4% |
Frequently asked questions
Is Gemini 3 Flash Preview better than GPT-4.1?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 35.9 on the Noometry Index.
Which is cheaper, Gemini 3 Flash Preview or GPT-4.1?
Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; GPT-4.1 lists at $2 and $8.
Is Gemini 3 Flash Preview or GPT-4.1 better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Gemini 3 Flash Preview does, with 1.05M tokens against 1.05M.
How many benchmarks do Gemini 3 Flash Preview and GPT-4.1 share?
38 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and GPT-4.1 has 52.