Gemini 3 Flash Preview vs GPT-5.4 Mini
Updated October 21, 2026. 42 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Gemini 3 Flash Preview for coding: it scores 75.8 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini.
Pick GPT-5.4 Mini when what matters is Vibe Code Bench (Vals AI) or Code migration (Vals AI), where it leads.
- Shared results
- 42
- Gemini 3 Flash Preview only
- 27
- GPT-5.4 Mini only
- 46
- Like-for-like categories
- 7 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, four public coding benchmarks
Gemini 3 Flash Preview
Gemini 3 Flash Preview scores 75.8 against 28.2.
One benchmark behind each score
Intelligence
AA Intelligence Index
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 26.3 against 24.1.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only GPT-5.4 Mini has a AA Agentic Index result, 17.9.
Directional only
Reasoning
GPQA Diamond
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 87.9% against 83.1%.
Same board, both measured
Math
AIME
No call
Tied at 95.6%.
Same board, both measured
Knowledge
MMLU Pro
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 88.6% against 84.5%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Gemini 3 Flash Preview has a Design Arena: websites result, 1196.
Directional only
Long documents
Listed context window
Gemini 3 Flash Preview
Gemini 3 Flash Preview takes 1.05M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 3 Flash Preview
Gemini 3 Flash Preview $0.0020, GPT-5.4 Mini $0.0030 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Gemini 3 Flash Preview
Gemini 3 Flash Preview $0.37, GPT-5.4 Mini $0.70.
Published attempt cost and pass rate
At a glance
- Coding index
- Gemini 3 Flash Preview 75.8 from 1 benchmark, GPT-5.4 Mini 28.2 from 1 benchmark.
- Widest category
- Reasoning, 10.4 points apart on average over 9 shared benchmarks.
- Widest single gap
- SimpleQA Verified: Gemini 3 Flash Preview 66.8% against GPT-5.4 Mini 29.4%, 37.4 points apart on a 0 to 100 scale.
- Output price
- Gemini 3 Flash Preview $3.00 against GPT-5.4 Mini $4.50 per million output tokens, 1.5x apart.
- Context window
- Gemini 3 Flash Preview takes 1.05M tokens, GPT-5.4 Mini 400K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Gemini 3 Flash Preview | Bars | GPT-5.4 Mini | Ties |
|---|---|---|---|---|
| Coding | 4 | 4 | 1 tie | |
| Intelligence | 1 | 0 | ||
| Agentic work | 3 | 3 | ||
| Reasoning | 9 | 0 | ||
| Math | 2 | 1 | 2 ties | |
| Knowledge | 6 | 0 | ||
| General | 5 | 1 | ||
| All shared boards | 30 | 9 | 3 ties |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index44
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 Mini | Leader |
|---|---|---|---|
| SWE-bench Verified | 75.8% | Not measured | Only Gemini 3 Flash Preview measured |
| LMArena WebDev | Not measured | 1397 | Only GPT-5.4 Mini measured |
| AA Coding Index | Not measured | 56.1 | Only GPT-5.4 Mini measured |
| LiveCodeBench (Vals AI) | 85.6% | 81.5% | Gemini 3 Flash Preview |
| SWE-bench Verified (Vals AI) | 75.0% | 73.0% | Gemini 3 Flash Preview |
| Terminal-Bench 4 (Vals AI) | Not measured | 2.5% | Only GPT-5.4 Mini measured |
| Vibe Code Bench (Vals AI) | 20.2% | 48.0% | GPT-5.4 Mini |
| Code migration (Vals AI) | 6.4% | 12.9% | GPT-5.4 Mini |
| ProgramBench (Vals AI) | 0.0% | 0.0% | Tie |
| Terminal-Bench 2.1 (Vals AI) | 53.9% | 54.7% | GPT-5.4 Mini |
| LiveCodeBench (Artificial Analysis run) | 90.8% | Not measured | Only Gemini 3 Flash Preview measured |
| SciCode | Not measured | 52.1% | Only GPT-5.4 Mini measured |
| Terminal-Bench Hard (Artificial Analysis run) | 38.6% | 52.3% | GPT-5.4 Mini |
| Terminal-Bench | 64.3% | Not measured | Only Gemini 3 Flash Preview measured |
| FrontierCode | Not measured | 27.0% | Only GPT-5.4 Mini measured |
| GSO-Bench | 9.8% | Not measured | Only Gemini 3 Flash Preview measured |
| WeirdML | 61.6% | 60.3% | Gemini 3 Flash Preview |
| ALE-Bench | 1367.2 | 1188.6 | Gemini 3 Flash Preview |
| LMArena Text: coding | Not measured | 1438 | Only GPT-5.4 Mini measured |
| LMArena Text: software and IT | Not measured | 1436 | Only GPT-5.4 Mini measured |
| LMArena WebDev: React | Not measured | 1386 | Only GPT-5.4 Mini measured |
| LMArena WebDev: HTML | Not measured | 1419 | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 26.3 | 24.1 | Gemini 3 Flash Preview |
| Epoch Capabilities Index | Not measured | 148.7 | Only GPT-5.4 Mini measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index33
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 Mini | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 17.9 | Only GPT-5.4 Mini measured |
| Design Arena: agents building web apps | 1111 | Not measured | Only Gemini 3 Flash Preview measured |
| Design Arena: agents building full-stack apps | 1063 | Not measured | Only Gemini 3 Flash Preview measured |
| Design Arena: agents building mobile apps | 1090 | Not measured | Only Gemini 3 Flash Preview measured |
| Design Arena: agents building Android apps | 1056 | Not measured | Only Gemini 3 Flash Preview measured |
| Design Arena: agents building Godot games | 1161 | Not measured | Only Gemini 3 Flash Preview measured |
| Design Arena: PowerPoint slides | 1036 | Not measured | Only Gemini 3 Flash Preview measured |
| Finance Agent (Vals AI) | 42.5% | 45.4% | GPT-5.4 Mini |
| Tax Agent Bench (Vals AI) | 11.8% | 8.8% | Gemini 3 Flash Preview |
| Legal Research Bench (Vals AI) | 18.3% | 12.5% | Gemini 3 Flash Preview |
| Excel Modeling Benchmark (Vals AI) | 26.0% | 45.4% | GPT-5.4 Mini |
| τ²-Bench Telecom | 80.4% | 83.3% | GPT-5.4 Mini |
| BALROG | 48.1% | Not measured | Only Gemini 3 Flash Preview measured |
| DeepResearch Bench | 49.8% | 36.3% | Gemini 3 Flash Preview |
| Vending-Bench 2 | $3,635 | Not measured | Only Gemini 3 Flash Preview measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | 87.9% | 83.1% | Gemini 3 Flash Preview |
| MMMU Pro (Vals AI) | 87.6% | 79.3% | Gemini 3 Flash Preview |
| GPQA Diamond (Artificial Analysis run) | 89.8% | 87.5% | Gemini 3 Flash Preview |
| Humanity's Last Exam (Artificial Analysis run) | 36.6% | 28.1% | Gemini 3 Flash Preview |
| GPQA Diamond (Epoch AI run) | 89.4% | 86.9% | Gemini 3 Flash Preview |
| ARC-AGI | 84.7% | 63.7% | Gemini 3 Flash Preview |
| ARC-AGI-2 | 33.6% | 18.9% | Gemini 3 Flash Preview |
| SimpleBench | 61.1% | Not measured | Only Gemini 3 Flash Preview measured |
| Chess puzzles | 39.0% | 23.0% | Gemini 3 Flash Preview |
| Mystery game puzzles | 26.0% | 11.0% | Gemini 3 Flash Preview |
| VPCT | 72.6% | Not measured | Only Gemini 3 Flash Preview measured |
| LMArena Text: hard prompts | Not measured | 1424 | Only GPT-5.4 Mini measured |
| LMArena Text: expert | Not measured | 1435 | Only GPT-5.4 Mini measured |
| LMArena Text: hard prompts in English | Not measured | 1420 | Only GPT-5.4 Mini measured |
| LMArena Vision: diagrams | Not measured | 1266 | Only GPT-5.4 Mini measured |
| LMArena Vision: homework | Not measured | 1285 | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 Mini | Leader |
|---|---|---|---|
| AIME | 95.6% | 95.6% | Tie |
| MGSM (Vals AI) | 93.3% | Not measured | Only Gemini 3 Flash Preview measured |
| AA Math Index | 97.0 | Not measured | Only Gemini 3 Flash Preview measured |
| AIME 2025 (Artificial Analysis run) | 97.0% | Not measured | Only Gemini 3 Flash Preview measured |
| OTIS Mock AIME | 95.6% | 88.9% | Gemini 3 Flash Preview |
| FrontierMath, tiers 1 to 3 | 51.2% | 51.2% | Tie |
| FrontierMath, tier 4 | 17.1% | 9.8% | Gemini 3 Flash Preview |
| ProofBench | 15.0% | 21.0% | GPT-5.4 Mini |
| LMArena Text: math | Not measured | 1418 | Only GPT-5.4 Mini measured |
| LMArena Text: mathematical work | Not measured | 1429 | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 Mini | Leader |
|---|---|---|---|
| MMLU Pro | 88.6% | 84.5% | Gemini 3 Flash Preview |
| LegalBench (Vals AI) | 86.9% | Not measured | Only Gemini 3 Flash Preview measured |
| CaseLaw (Vals AI) | 55.8% | 51.7% | Gemini 3 Flash Preview |
| CorpFin (Vals AI) | 66.4% | 60.9% | Gemini 3 Flash Preview |
| TaxEval (Vals AI) | 73.9% | 71.2% | Gemini 3 Flash Preview |
| MortgageTax (Vals AI) | 68.7% | 63.5% | Gemini 3 Flash Preview |
| MedQA (Vals AI) | 95.8% | Not measured | Only Gemini 3 Flash Preview measured |
| MedCode (Vals AI) | 55.9% | Not measured | Only Gemini 3 Flash Preview measured |
| MMLU Pro (Artificial Analysis run) | 89.0% | Not measured | Only Gemini 3 Flash Preview measured |
| SimpleQA Verified | 66.8% | 29.4% | Gemini 3 Flash Preview |
| GeoBench | 88.0% | Not measured | Only Gemini 3 Flash Preview measured |
| LMArena Text: science | Not measured | 1417 | Only GPT-5.4 Mini measured |
| LMArena Text: medicine and healthcare | Not measured | 1395 | Only GPT-5.4 Mini measured |
| LMArena Text: legal and government | Not measured | 1414 | Only GPT-5.4 Mini measured |
| LMArena Text: business and finance | Not measured | 1418 | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 2 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 1196 | Not measured | Only Gemini 3 Flash Preview measured |
| Design Arena: game dev | 1166 | Not measured | Only Gemini 3 Flash Preview measured |
| Design Arena: 3D | 1184 | Not measured | Only Gemini 3 Flash Preview measured |
| Design Arena: all code categories | 1189 | Not measured | Only Gemini 3 Flash Preview measured |
| Neither model has a result on the other 5 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 Mini | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 51.8% | 50.8% | Gemini 3 Flash Preview |
| MedScribe (Vals AI) | 69.9% | Not measured | Only Gemini 3 Flash Preview measured |
| Vals Multimodal Index | 52.2% | 54.2% | GPT-5.4 Mini |
| IFBench | 78.0% | 73.3% | Gemini 3 Flash Preview |
| Long context reasoning (AA-LCR) | 78.0% | 77.0% | Gemini 3 Flash Preview |
| DTBench | 89.1% | 80.0% | Gemini 3 Flash Preview |
| LMCA | 43.1% | 40.8% | Gemini 3 Flash Preview |
| LMArena Text | Not measured | 1412 | Only GPT-5.4 Mini measured |
| LMArena Text: instruction following | Not measured | 1405 | Only GPT-5.4 Mini measured |
| LMArena Text: creative writing | Not measured | 1370 | Only GPT-5.4 Mini measured |
| LMArena Vision | Not measured | 1245 | Only GPT-5.4 Mini measured |
| LMArena Text: English | Not measured | 1412 | Only GPT-5.4 Mini measured |
| LMArena Text: non-English | Not measured | 1405 | Only GPT-5.4 Mini measured |
| LMArena Text: Chinese | Not measured | 1446 | Only GPT-5.4 Mini measured |
| LMArena Text: German | Not measured | 1408 | Only GPT-5.4 Mini measured |
| LMArena Text: Japanese | Not measured | 1375 | Only GPT-5.4 Mini measured |
| LMArena Text: Korean | Not measured | 1370 | Only GPT-5.4 Mini measured |
| LMArena Text: French | Not measured | 1441 | Only GPT-5.4 Mini measured |
| LMArena Text: Spanish | Not measured | 1405 | Only GPT-5.4 Mini measured |
| LMArena Text: Russian | Not measured | 1417 | Only GPT-5.4 Mini measured |
| LMArena Text: Polish | Not measured | 1415 | Only GPT-5.4 Mini measured |
| LMArena Text: multi-turn | Not measured | 1429 | Only GPT-5.4 Mini measured |
| LMArena Text: longer queries | Not measured | 1408 | Only GPT-5.4 Mini measured |
| LMArena Text: writing and language | Not measured | 1393 | Only GPT-5.4 Mini measured |
| LMArena Text: entertainment and media | Not measured | 1373 | Only GPT-5.4 Mini measured |
| LMArena Vision: English | Not measured | 1244 | Only GPT-5.4 Mini measured |
| LMArena Vision: Chinese | Not measured | 1286 | Only GPT-5.4 Mini measured |
| LMArena Vision: reading text | Not measured | 1253 | Only GPT-5.4 Mini measured |
| LMArena Vision: humor | Not measured | 1235 | Only GPT-5.4 Mini measured |
| LMArena Vision: recognizing things | Not measured | 1218 | Only GPT-5.4 Mini measured |
| LMArena Vision: creative writing | Not measured | 1222 | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 3 Flash Preview | GPT-5.4 Mini | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemini 3 Flash Preview costs less
Repository review
50K input + 3K output tokens
Gemini 3 Flash Preview costs less
Agent loop
200K input + 10K output tokens
Gemini 3 Flash Preview costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Google Gemini 3 Flash Preview | OpenAI GPT-5.4 Mini |
|---|---|---|
| Maker | OpenAI | |
| Weights | No public weights listed | No public weights listed |
| Released | December 17, 2025 | March 17, 2026 |
| Context window | 1.05M | 400K |
| Input $/Mtok | $0.50 | $0.75 |
| Output $/Mtok | $3.00 | $4.50 |
| Coding index | 75.8 | 28.2 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $0.37 | $0.70 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 3 Flash Preview better than GPT-5.4 Mini for coding?
Pick Gemini 3 Flash Preview for coding: it scores 75.8 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini. Pick GPT-5.4 Mini when what matters is Vibe Code Bench (Vals AI) or Code migration (Vals AI), where it leads.
Which is cheaper, Gemini 3 Flash Preview or GPT-5.4 Mini?
Gemini 3 Flash Preview costs $0.50 per million input tokens and $3.00 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Per solved SWE-bench Verified task, Gemini 3 Flash Preview costs $0.37 and GPT-5.4 Mini $0.70.
Which has the bigger context window, Gemini 3 Flash Preview or GPT-5.4 Mini?
Gemini 3 Flash Preview, with 1.05M tokens against 400K.
How many benchmarks is the Gemini 3 Flash Preview vs GPT-5.4 Mini comparison based on?
42 benchmarks have a result for both models as of October 21, 2026. Gemini 3 Flash Preview's coding index rests on 1 independent benchmark and GPT-5.4 Mini's on 1. Where only one model has a result, the page says so instead of naming a winner.