Gemini 2.5 Flash Lite vs GPT-4.1 Mini
Gemini 2.5 Flash Lite leads GPT-4.1 Mini on the Artificial Analysis Intelligence Index, 10.4 to 10.2, and Gemini 2.5 Flash Lite costs 4.0x less per output token ($0.40 vs $1.60 per million). Updated October 21, 2026; 27 benchmarks have a result for both.
Gemini 2.5 Flash Lite or GPT-4.1 Mini: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Gemini 2.5 Flash Lite for output tokens 4.0x cheaper ($0.40 vs $1.60 per million) and a larger context window (1.05M against 1.05M tokens).
- Shared results
- 27
- Gemini 2.5 Flash Lite only
- 3
- GPT-4.1 Mini only
- 59
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Gemini 2.5 Flash Lite
Gemini 2.5 Flash Lite leads, 10.4 against 10.2.
Same board, both measured
Reasoning
GPQA Diamond
Gemini 2.5 Flash Lite
Gemini 2.5 Flash Lite leads, 70.2% against 67.9%.
Same board, both measured
Math
AIME
GPT-4.1 Mini
GPT-4.1 Mini leads, 49.4% against 42.1%.
Same board, both measured
Knowledge
MMLU Pro
Gemini 2.5 Flash Lite
Gemini 2.5 Flash Lite leads, 79.1% against 77.2%.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-4.1 Mini has a Design Arena: websites result, 997.
Directional only
Long documents
Listed context window
Gemini 2.5 Flash Lite
Gemini 2.5 Flash Lite takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 2.5 Flash Lite
Gemini 2.5 Flash Lite $0.0003, GPT-4.1 Mini $0.0012 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-4.1 Mini has the number, $1.818.
Directional only
At a glance
- Coding index
- Gemini 2.5 Flash Lite not benchmarked, GPT-4.1 Mini not benchmarked.
- Widest category
- Agentic work, 23.7 points apart on average over 2 shared benchmarks.
- Widest single gap
- τ²-Bench Telecom: Gemini 2.5 Flash Lite 19.0% against GPT-4.1 Mini 52.9%, 33.9 points apart on a 0 to 100 scale.
- Output price
- Gemini 2.5 Flash Lite $0.40 against GPT-4.1 Mini $1.60 per million output tokens, 4.0x apart.
- Context window
- Gemini 2.5 Flash Lite takes 1.05M tokens, GPT-4.1 Mini 1.05M.
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 2.5 Flash Lite | Bars | GPT-4.1 Mini | Ties |
|---|---|---|---|---|
| Coding | 2 | 1 | ||
| Intelligence | 1 | 1 | ||
| Agentic work | 0 | 2 | ||
| Reasoning | 3 | 2 | ||
| Math | 3 | 1 | ||
| Knowledge | 3 | 4 | ||
| General | 2 | 2 | ||
| All shared boards | 14 | 13 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index21
| Benchmark | Gemini 2.5 Flash Lite | GPT-4.1 Mini | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 32.4% | Only GPT-4.1 Mini measured |
| SWE-bench Verified | Not measured | 23.9% | Only GPT-4.1 Mini measured |
| AA Coding Index | Not measured | 20.2 | Only GPT-4.1 Mini measured |
| LiveCodeBench (Vals AI) | 71.4% | 58.2% | Gemini 2.5 Flash Lite |
| LiveCodeBench (Artificial Analysis run) | 59.3% | 48.3% | Gemini 2.5 Flash Lite |
| Terminal-Bench Hard (Artificial Analysis run) | 4.5% | 7.6% | GPT-4.1 Mini |
| WeirdML | Not measured | 37.6% | Only GPT-4.1 Mini measured |
| LMArena Text: coding | Not measured | 1367 | Only GPT-4.1 Mini measured |
| LMArena Text: software and IT | Not measured | 1360 | Only GPT-4.1 Mini measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Gemini 2.5 Flash Lite | GPT-4.1 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.4 | 10.2 | Gemini 2.5 Flash Lite |
| Epoch Capabilities Index | 133.8 | 134.9 | GPT-4.1 Mini |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Gemini 2.5 Flash Lite | GPT-4.1 Mini | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 19.0% | 52.9% | GPT-4.1 Mini |
| Berkeley Function Calling Leaderboard (BFCL) | 36.9% | 50.4% | GPT-4.1 Mini |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | Gemini 2.5 Flash Lite | GPT-4.1 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | 70.2% | 67.9% | Gemini 2.5 Flash Lite |
| MMMU Pro (Vals AI) | 75.4% | 70.5% | Gemini 2.5 Flash Lite |
| GPQA Diamond (Artificial Analysis run) | 62.5% | 66.4% | GPT-4.1 Mini |
| Humanity's Last Exam (Artificial Analysis run) | 6.8% | 5.0% | Gemini 2.5 Flash Lite |
| GPQA Diamond (Epoch AI run) | Not measured | 65.8% | Only GPT-4.1 Mini measured |
| ARC-AGI | Not measured | 3.5% | Only GPT-4.1 Mini measured |
| ARC-AGI-2 | Not measured | 0.0% | Only GPT-4.1 Mini measured |
| Chess puzzles | Not measured | 1.0% | Only GPT-4.1 Mini measured |
| Mystery game puzzles | Not measured | 7.0% | Only GPT-4.1 Mini measured |
| LMArena Text: hard prompts | Not measured | 1349 | Only GPT-4.1 Mini measured |
| LMArena Text: expert | Not measured | 1338 | Only GPT-4.1 Mini measured |
| LMArena Text: hard prompts in English | Not measured | 1362 | Only GPT-4.1 Mini measured |
| LMArena Vision: diagrams | Not measured | 1182 | Only GPT-4.1 Mini measured |
| LMArena Vision: homework | Not measured | 1214 | Only GPT-4.1 Mini measured |
| Kagi LLM Benchmark | 40.5% | 48.6% | GPT-4.1 Mini |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | Gemini 2.5 Flash Lite | GPT-4.1 Mini | Leader |
|---|---|---|---|
| AIME | 42.1% | 49.4% | GPT-4.1 Mini |
| MATH 500 (Vals AI) | Not measured | 88.0% | Only GPT-4.1 Mini measured |
| MGSM (Vals AI) | 89.5% | 87.8% | Gemini 2.5 Flash Lite |
| AA Math Index | 53.3 | 46.3 | Gemini 2.5 Flash Lite |
| AIME 2025 (Artificial Analysis run) | 53.3% | 46.3% | Gemini 2.5 Flash Lite |
| OTIS Mock AIME | Not measured | 44.7% | Only GPT-4.1 Mini measured |
| FrontierMath, tiers 1 to 3 | Not measured | 6.7% | Only GPT-4.1 Mini measured |
| MATH level 5 | Not measured | 87.3% | Only GPT-4.1 Mini measured |
| LMArena Text: math | Not measured | 1343 | Only GPT-4.1 Mini measured |
| LMArena Text: mathematical work | Not measured | 1347 | Only GPT-4.1 Mini measured |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index34
| Benchmark | Gemini 2.5 Flash Lite | GPT-4.1 Mini | Leader |
|---|---|---|---|
| MMLU Pro | 79.1% | 77.2% | Gemini 2.5 Flash Lite |
| LegalBench (Vals AI) | 82.0% | 78.0% | Gemini 2.5 Flash Lite |
| CorpFin (Vals AI) | 57.6% | 57.9% | GPT-4.1 Mini |
| TaxEval (Vals AI) | 66.2% | 71.9% | GPT-4.1 Mini |
| MortgageTax (Vals AI) | 57.6% | 65.5% | GPT-4.1 Mini |
| MedQA (Vals AI) | 88.9% | 84.6% | Gemini 2.5 Flash Lite |
| MedCode (Vals AI) | 34.2% | Not measured | Only Gemini 2.5 Flash Lite measured |
| MMLU Pro (Artificial Analysis run) | 75.9% | 78.1% | GPT-4.1 Mini |
| SimpleQA Verified | Not measured | 12.7% | Only GPT-4.1 Mini measured |
| LMArena Text: science | Not measured | 1328 | Only GPT-4.1 Mini measured |
| LMArena Text: medicine and healthcare | Not measured | 1324 | Only GPT-4.1 Mini measured |
| LMArena Text: legal and government | Not measured | 1343 | Only GPT-4.1 Mini measured |
| LMArena Text: business and finance | Not measured | 1322 | Only GPT-4.1 Mini measured |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Gemini 2.5 Flash Lite | GPT-4.1 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 997 | Only GPT-4.1 Mini measured |
| Design Arena: UI components | Not measured | 961 | Only GPT-4.1 Mini measured |
| Design Arena: game dev | Not measured | 1071 | Only GPT-4.1 Mini measured |
| Design Arena: data viz | Not measured | 1034 | Only GPT-4.1 Mini measured |
| Design Arena: 3D | Not measured | 837 | Only GPT-4.1 Mini measured |
| Design Arena: all code categories | Not measured | 994 | Only GPT-4.1 Mini measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | Gemini 2.5 Flash Lite | GPT-4.1 Mini | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 30.8% | Not measured | Only Gemini 2.5 Flash Lite measured |
| MedScribe (Vals AI) | 75.8% | Not measured | Only Gemini 2.5 Flash Lite measured |
| IFBench | 49.9% | 38.3% | Gemini 2.5 Flash Lite |
| Long context reasoning (AA-LCR) | 55.7% | 44.0% | Gemini 2.5 Flash Lite |
| DTBench | 62.8% | 68.8% | GPT-4.1 Mini |
| LMCA | 18.1% | 21.1% | GPT-4.1 Mini |
| Fiction.LiveBench | Not measured | 44.4% | Only GPT-4.1 Mini measured |
| LMArena Text | Not measured | 1341 | Only GPT-4.1 Mini measured |
| LMArena Text: instruction following | Not measured | 1333 | Only GPT-4.1 Mini measured |
| LMArena Text: creative writing | Not measured | 1299 | Only GPT-4.1 Mini measured |
| LMArena Vision | Not measured | 1181 | Only GPT-4.1 Mini measured |
| LMArena Text: English | Not measured | 1356 | Only GPT-4.1 Mini measured |
| LMArena Text: non-English | Not measured | 1318 | Only GPT-4.1 Mini measured |
| LMArena Text: Chinese | Not measured | 1329 | Only GPT-4.1 Mini measured |
| LMArena Text: German | Not measured | 1350 | Only GPT-4.1 Mini measured |
| LMArena Text: Japanese | Not measured | 1290 | Only GPT-4.1 Mini measured |
| LMArena Text: Korean | Not measured | 1298 | Only GPT-4.1 Mini measured |
| LMArena Text: French | Not measured | 1358 | Only GPT-4.1 Mini measured |
| LMArena Text: Spanish | Not measured | 1319 | Only GPT-4.1 Mini measured |
| LMArena Text: Russian | Not measured | 1324 | Only GPT-4.1 Mini measured |
| LMArena Text: Polish | Not measured | 1326 | Only GPT-4.1 Mini measured |
| LMArena Text: multi-turn | Not measured | 1354 | Only GPT-4.1 Mini measured |
| LMArena Text: longer queries | Not measured | 1344 | Only GPT-4.1 Mini measured |
| LMArena Text: writing and language | Not measured | 1319 | Only GPT-4.1 Mini measured |
| LMArena Text: entertainment and media | Not measured | 1300 | Only GPT-4.1 Mini measured |
| LMArena Vision: English | Not measured | 1191 | Only GPT-4.1 Mini measured |
| LMArena Vision: Chinese | Not measured | 1186 | Only GPT-4.1 Mini measured |
| LMArena Vision: reading text | Not measured | 1188 | Only GPT-4.1 Mini measured |
| LMArena Vision: humor | Not measured | 1182 | Only GPT-4.1 Mini measured |
| LMArena Vision: captioning | Not measured | 1174 | Only GPT-4.1 Mini measured |
| LMArena Vision: recognizing things | Not measured | 1187 | Only GPT-4.1 Mini measured |
| LMArena Vision: creative writing | Not measured | 1182 | Only GPT-4.1 Mini measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 2.5 Flash Lite | GPT-4.1 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 2.5 Flash Lite costs less
Repository review
50K input + 3K output tokens
Gemini 2.5 Flash Lite costs less
Agent loop
200K input + 10K output tokens
Gemini 2.5 Flash Lite 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 2.5 Flash Lite | OpenAI GPT-4.1 Mini |
|---|---|---|
| Maker | OpenAI | |
| Weights | No public weights listed | No public weights listed |
| Released | July 22, 2025 | April 14, 2025 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.10 | $0.40 |
| Output $/Mtok | $0.40 | $1.60 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | $1.818 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 2.5 Flash Lite better than GPT-4.1 Mini for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemini 2.5 Flash Lite for output tokens 4.0x cheaper ($0.40 vs $1.60 per million) and a larger context window (1.05M against 1.05M tokens).
Which is cheaper, Gemini 2.5 Flash Lite or GPT-4.1 Mini?
Gemini 2.5 Flash Lite costs $0.10 per million input tokens and $0.40 per million output tokens; GPT-4.1 Mini costs $0.40 and $1.60. Cost per solved task is known for GPT-4.1 Mini only.
Which has the bigger context window, Gemini 2.5 Flash Lite or GPT-4.1 Mini?
Gemini 2.5 Flash Lite, with 1.05M tokens against 1.05M.
How many benchmarks is the Gemini 2.5 Flash Lite vs GPT-4.1 Mini comparison based on?
27 benchmarks have a result for both models as of October 21, 2026. Gemini 2.5 Flash Lite's coding index rests on 0 independent benchmarks and GPT-4.1 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.