Model comparison
Gemini 3 Flash Preview vs GPT-5 Mini
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 41.8 on the Noometry Index. GPT-5 Mini costs 1.6× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.
Last verified . 43 shared benchmarks.
GoogleSummary
- They share 43 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 9 categories and GPT-5 Mini in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 23.9.
- The biggest single-benchmark swing is SimpleQA Verified: 66.8% for Gemini 3 Flash Preview and 21.6% for GPT-5 Mini.
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 400K.
Side by side
| Gemini 3 Flash Preview | GPT-5 Mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 52.3 | 41.8 |
| Released | 2025-12-17 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.50 | $0.25 |
| Output $ / M tokens | $3 | $2 |
| Results tracked | 59 | 60 |
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 Mini: 40.1 (#146)
| Benchmark | Gemini 3 Flash Preview | GPT-5 Mini |
|---|---|---|
| SWE-bench Verified | 75.4% | 64.7% |
| SWE-bench Verified (bash only) | 75.8% | 59.8% |
| SWE-bench Multilingual | 72.7% | 39.7% |
| WeirdML | 61.6% | 52.7% |
| LMArena Coding | 1460 | 1406 |
| ALE-Bench | 1,367 | 799.77 |
| LMArena WebDev | 1439 | — |
| SciCode | — | 39.2% |
| GSO | 9.8% | — |
| AlgoTune | — | 1.38 |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 38.7 (#29), GPT-5 Mini: 31.1 (#70)
| Benchmark | Gemini 3 Flash Preview | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | 64.3% | 34.8% |
| Vending-Bench 2 | 3,635 | -31.18 |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| 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 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), GPT-5 Mini: 23.9 (#168)
| Benchmark | Gemini 3 Flash Preview | GPT-5 Mini |
|---|---|---|
| ARC-AGI-2 | 33.6% | 4.4% |
| ARC-AGI-1 | 84.7% | 54.3% |
| Chess Puzzles | 40% | 30% |
| LMArena Hard Prompts | 1465 | 1380 |
| Mystery Game Puzzles | 26% | 10% |
| DTBench | 89.1% | 80.5% |
| LMCA | 43.1% | 34.2% |
| Epoch Capabilities Index | 151.8 | 145.52 |
| ForecastBench | 58.5 | 61 |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | — | 70.3% |
| NYT Connections (extended) | 83.1% | — |
| CritPt | — | 0% |
| EnigmaEval | — | 8.2% |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.7 (#55), GPT-5 Mini: 46.7 (#69)
| Benchmark | Gemini 3 Flash Preview | GPT-5 Mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 46.7% |
| FrontierMath Tier 4 | 17.1% | 12.2% |
| OTIS Mock AIME 2024-2025 | 95.6% | 86.7% |
| ProofBench | 15% | 9% |
| LMArena Math | 1473 | 1378 |
| FrontierMath (Feb 2025 set) | 35.6% | 27.2% |
| FrontierMath Tier 4 (v1) | 4.2% | 6.3% |
| MathArena Final-Answer Competitions | 67.6% | — |
| Omni-MATH | — | 72.2% |
| MATH Level 5 | — | 97.8% |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), GPT-5 Mini: 45.6 (#86)
| Benchmark | Gemini 3 Flash Preview | GPT-5 Mini |
|---|---|---|
| GPQA Diamond | 89.4% | 75% |
| SimpleQA Verified | 66.8% | 21.6% |
| Vectara Hallucination Rate | 13.5% | 12.9% |
| LMArena Expert | 1462 | 1379 |
| Humanity's Last Exam | — | 19.4% |
| MMLU-Pro | — | 83.5% |
| Confabulations | — | 13.3% |
| GPQA (HELM) | — | 75.6% |
Multimodal Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 45.5 (#16), GPT-5 Mini: 35.6 (#85)
| Benchmark | Gemini 3 Flash Preview | GPT-5 Mini |
|---|---|---|
| LMArena Vision | 1285 | 1202 |
| VPCT | 72.6% | 40.2% |
| GeoBench | 88% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |
Multilingual Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 55.7 (#27), GPT-5 Mini: 48.9 (#137)
| Benchmark | Gemini 3 Flash Preview | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1458 | 1363 |
| LMArena Chinese | 1511 | 1385 |
| LMArena French | 1477 | 1386 |
| LMArena German | 1497 | 1366 |
| LMArena Japanese | 1489 | 1341 |
| LMArena Korean | 1443 | 1308 |
| LMArena Russian | 1480 | 1362 |
| LMArena Spanish | 1469 | 1355 |
Instruction Following Too close to call
Gemini 3 Flash Preview: 75.7 (#56), GPT-5 Mini: 76.2 (#46)
| Benchmark | Gemini 3 Flash Preview | GPT-5 Mini |
|---|---|---|
| LMArena Instruction Following | 1437 | 1357 |
| IFEval | — | 92.7% |
Long Context Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 44.4 (#67), GPT-5 Mini: 41.9 (#132)
| Benchmark | Gemini 3 Flash Preview | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1452 | 1355 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 65.5 (#45), GPT-5 Mini: 55.2 (#148)
| Benchmark | Gemini 3 Flash Preview | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1466 | 1373 |
| LMArena Creative Writing | 1457 | 1325 |
| LMArena Multi-Turn | 1471 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| EQ-Bench Creative Writing | — | 1313 |
| WildBench | — | 85.5% |
Frequently asked questions
Is Gemini 3 Flash Preview better than GPT-5 Mini?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 41.8 on the Noometry Index. GPT-5 Mini costs 1.6× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.
Which is cheaper, Gemini 3 Flash Preview or GPT-5 Mini?
GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.
Is Gemini 3 Flash Preview or GPT-5 Mini better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 40.1 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 Mini share?
43 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and GPT-5 Mini has 60.