Model comparison
Gemini 3 Flash Preview vs GPT-5.4 mini
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 45.0 on the Noometry Index.
Last verified . 40 shared benchmarks.
GoogleSummary
- They share 40 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 10 categories and GPT-5.4 mini 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 30.4.
- The biggest single-benchmark swing is SimpleQA Verified: 66.8% for Gemini 3 Flash Preview and 29.4% for GPT-5.4 mini.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 400K.
Side by side
| Gemini 3 Flash Preview | GPT-5.4 mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 52.3 | 45.0 |
| Released | 2025-12-17 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.50 | $0.75 |
| Output $ / M tokens | $3 | $4.50 |
| Results tracked | 59 | 46 |
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-5.4 mini: 45.2 (#72)
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 mini |
|---|---|---|
| LMArena WebDev | 1439 | 1397 |
| WeirdML | 61.6% | 60.3% |
| LMArena Coding | 1460 | 1438 |
| ALE-Bench | 1,367 | 1,189 |
| SWE-bench Verified | 75.4% | — |
| FrontierCode | — | 27% |
| SWE-bench Verified (bash only) | 75.8% | — |
| SWE-bench Multilingual | 72.7% | — |
| SciCode | — | 49.9% |
| GSO | 9.8% | — |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 38.7 (#29), GPT-5.4 mini: 29.9 (#81)
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | 49.8% | 36.3% |
| Terminal-Bench | 64.3% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| 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-5.4 mini: 30.4 (#85)
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 mini |
|---|---|---|
| ARC-AGI-2 | 33.6% | 18.9% |
| NYT Connections (extended) | 83.1% | 61.8% |
| ARC-AGI-1 | 84.7% | 63.7% |
| Chess Puzzles | 40% | 24% |
| LMArena Hard Prompts | 1465 | 1424 |
| Mystery Game Puzzles | 26% | 11% |
| DTBench | 89.1% | 80% |
| LMCA | 43.1% | 40.8% |
| Epoch Capabilities Index | 151.8 | 148.84 |
| ForecastBench | 58.5 | 57 |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | — | 37.9% |
| CritPt | — | 10% |
| Thematic Generalization | — | 61.7% |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.7 (#55), GPT-5.4 mini: 45.5 (#75)
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 51.2% |
| FrontierMath Tier 4 | 17.1% | 9.8% |
| OTIS Mock AIME 2024-2025 | 95.6% | 88.9% |
| ProofBench | 15% | 21% |
| LMArena Math | 1473 | 1419 |
| FrontierMath (Feb 2025 set) | 35.6% | 28.3% |
| FrontierMath Tier 4 (v1) | 4.2% | 2.1% |
| MathArena Final-Answer Competitions | 67.6% | — |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), GPT-5.4 mini: 51.5 (#67)
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 89.4% | 86.9% |
| SimpleQA Verified | 66.8% | 29.4% |
| Vectara Hallucination Rate | 13.5% | 5.5% |
| LMArena Expert | 1462 | 1435 |
Multimodal Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 45.5 (#16), GPT-5.4 mini: 39.7 (#56)
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | 1285 | 1245 |
| 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-5.4 mini: 51.9 (#96)
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1458 | 1405 |
| LMArena Chinese | 1511 | 1446 |
| LMArena French | 1477 | 1440 |
| LMArena German | 1497 | 1409 |
| LMArena Japanese | 1489 | 1374 |
| LMArena Korean | 1443 | 1368 |
| LMArena Russian | 1480 | 1417 |
| LMArena Spanish | 1469 | 1405 |
Instruction Following Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 75.7 (#56), GPT-5.4 mini: 74.1 (#102)
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1437 | 1405 |
Long Context Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 44.4 (#67), GPT-5.4 mini: 43.0 (#112)
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1452 | 1407 |
Writing & Preference Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 65.5 (#45), GPT-5.4 mini: 64.0 (#58)
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1466 | 1412 |
| LMArena Creative Writing | 1457 | 1370 |
| LMArena Multi-Turn | 1471 | 1429 |
| EQ-Bench Creative Writing | — | 1665 |
Frequently asked questions
Is Gemini 3 Flash Preview better than GPT-5.4 mini?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 45.0 on the Noometry Index.
Which is cheaper, Gemini 3 Flash Preview or GPT-5.4 mini?
Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is Gemini 3 Flash Preview or GPT-5.4 mini better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 45.2 in the Noometry coding category.
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-5.4 mini share?
40 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and GPT-5.4 mini has 46.