Model comparison
Gemini 3 Flash Preview vs GPT-4
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 29.1 on the Noometry Index.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 8 categories and GPT-4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3 Flash Preview leads 51.7 to 10.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3 Flash Preview and 1.1% for GPT-4.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $30 / $60 for GPT-4.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 8K.
Side by side
| Gemini 3 Flash Preview | GPT-4 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 52.3 | 29.1 |
| Released | 2025-12-17 | 2023-03-14 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 8K |
| Max output | 66K | 8K |
| Input $ / M tokens | $0.50 | $30 |
| Output $ / M tokens | $3 | $60 |
| Results tracked | 59 | 38 |
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: 31.6 (#283)
| Benchmark | Gemini 3 Flash Preview | GPT-4 |
|---|---|---|
| WeirdML | 61.6% | 12.4% |
| LMArena Coding | 1460 | 1254 |
| SWE-bench Verified | 75.4% | — |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 72.7% | — |
| GSO | 9.8% | — |
| BigCodeBench Instruct | — | 46% |
| BigCodeBench Complete | — | 57.2% |
| ALE-Bench | 1,367 | — |
| HumanEval+ | — | 79.3% |
Agentic & Tool Use Not comparable
Gemini 3 Flash Preview: 38.7 (#29), GPT-4: —
| Benchmark | Gemini 3 Flash Preview | GPT-4 |
|---|---|---|
| Terminal-Bench | 64.3% | — |
| 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% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
| METR Time Horizons | — | 36.1% |
| Vending-Bench 2 | 3,635 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), GPT-4: 17.8 (#289)
| Benchmark | Gemini 3 Flash Preview | GPT-4 |
|---|---|---|
| Chess Puzzles | 40% | 4% |
| LMArena Hard Prompts | 1465 | 1241 |
| Mystery Game Puzzles | 26% | 12% |
| DTBench | 89.1% | 62.7% |
| LMCA | 43.1% | 17.1% |
| Epoch Capabilities Index | 151.8 | 125.89 |
| ForecastBench | 58.5 | 57.8 |
| ARC-AGI-2 | 33.6% | — |
| SimpleBench | 61.1% | — |
| NYT Connections (extended) | 83.1% | — |
| ARC-AGI-1 | 84.7% | — |
| BIG-Bench Hard | — | 75.1% |
| HellaSwag | — | 95.3% |
| WinoGrande | — | 87.5% |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.7 (#55), GPT-4: 10.8 (#309)
| Benchmark | Gemini 3 Flash Preview | GPT-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 1.1% |
| LMArena Math | 1473 | 1269 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 15% | — |
| MATH Level 5 | — | 23% |
| FrontierMath (Feb 2025 set) | 35.6% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
| GSM8K | — | 92% |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), GPT-4: 18.4 (#282)
| Benchmark | Gemini 3 Flash Preview | GPT-4 |
|---|---|---|
| GPQA Diamond | 89.4% | 35.7% |
| LMArena Expert | 1462 | 1211 |
| SimpleQA Verified | 66.8% | — |
| Vectara Hallucination Rate | 13.5% | — |
| MMLU | — | 86.4% |
| TriviaQA | — | 84.8% |
Multimodal Not comparable
Gemini 3 Flash Preview: 45.5 (#16), GPT-4: —
| Benchmark | Gemini 3 Flash Preview | GPT-4 |
|---|---|---|
| LMArena Vision | 1285 | — |
| GeoBench | 88% | — |
| 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: 40.6 (#215)
| Benchmark | Gemini 3 Flash Preview | GPT-4 |
|---|---|---|
| LMArena Non-English | 1458 | 1246 |
| LMArena Chinese | 1511 | 1242 |
| LMArena French | 1477 | 1283 |
| LMArena German | 1497 | 1251 |
| LMArena Japanese | 1489 | 1209 |
| LMArena Korean | 1443 | 1184 |
| LMArena Russian | 1480 | 1251 |
| LMArena Spanish | 1469 | 1261 |
Instruction Following Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 75.7 (#56), GPT-4: 65.3 (#222)
| Benchmark | Gemini 3 Flash Preview | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 1437 | 1241 |
Long Context Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 44.4 (#67), GPT-4: 37.7 (#212)
| Benchmark | Gemini 3 Flash Preview | GPT-4 |
|---|---|---|
| LMArena Longer Query | 1452 | 1244 |
Writing & Preference Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 65.5 (#45), GPT-4: 34.9 (#268)
| Benchmark | Gemini 3 Flash Preview | GPT-4 |
|---|---|---|
| LMArena Text | 1466 | 1263 |
| LMArena Creative Writing | 1457 | 1244 |
| LMArena Multi-Turn | 1471 | 1257 |
| EQ-Bench Creative Writing | — | 752 |
Frequently asked questions
Is Gemini 3 Flash Preview better than GPT-4?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 29.1 on the Noometry Index.
Which is cheaper, Gemini 3 Flash Preview or GPT-4?
Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; GPT-4 lists at $30 and $60.
Is Gemini 3 Flash Preview or GPT-4 better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 31.6 in the Noometry coding category.
Which has the bigger context window?
Gemini 3 Flash Preview does, with 1.05M tokens against 8K.
How many benchmarks do Gemini 3 Flash Preview and GPT-4 share?
26 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and GPT-4 has 38.