Model comparison
Gemini 3.5 Flash Lite vs GPT-4.1 nano
Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 27.9 on the Noometry Index. GPT-4.1 nano costs 4.9× less per token, which makes it the better buy when Gemini 3.5 Flash Lite's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 8 categories and GPT-4.1 nano in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.5 Flash Lite leads 50.1 to 21.8.
- The biggest single-benchmark swing is ARC-AGI-1: 53.5% for Gemini 3.5 Flash Lite and 0% for GPT-4.1 nano.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.30 / $2.50 for Gemini 3.5 Flash Lite.
- Gemini 3.5 Flash Lite accepts more context: 1.05M tokens versus 1.05M.
Side by side
| Gemini 3.5 Flash Lite | GPT-4.1 nano | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 41.5 | 27.9 |
| Released | 2026-07-21 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 33K |
| Input $ / M tokens | $0.30 | $0.10 |
| Output $ / M tokens | $2.50 | $0.40 |
| Results tracked | 39 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 42.4 (#104), GPT-4.1 nano: 24.1 (#330)
| Benchmark | Gemini 3.5 Flash Lite | GPT-4.1 nano |
|---|---|---|
| SciCode | 41.3% | 25.9% |
| WeirdML | 39% | 19% |
| LMArena Coding | 1453 | 1306 |
| Aider Polyglot | — | 8.9% |
| LMArena WebDev | 1440 | — |
| ALE-Bench | 765.27 | — |
Agentic & Tool Use Too close to call
Gemini 3.5 Flash Lite: 25.7 (#107), GPT-4.1 nano: 26.5 (#104)
| Benchmark | Gemini 3.5 Flash Lite | GPT-4.1 nano |
|---|---|---|
| APEX-Agents | 29.3% | — |
| Berkeley Function Calling Leaderboard | — | 33% |
| GDP.pdf | 10% | — |
Reasoning Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 27.8 (#114), GPT-4.1 nano: 8.5 (#349)
| Benchmark | Gemini 3.5 Flash Lite | GPT-4.1 nano |
|---|---|---|
| ARC-AGI-2 | 10.3% | 0% |
| ARC-AGI-1 | 53.5% | 0% |
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1441 | 1286 |
| DTBench | 83.5% | 52.5% |
| LMCA | 37.6% | 5.5% |
| Epoch Capabilities Index | 145.13 | 129.62 |
| Kagi LLM Benchmark | — | 33.3% |
| NYT Connections (extended) | 60.4% | — |
| Chess Puzzles | 22% | — |
| Mystery Game Puzzles | 19% | — |
Math GPT-4.1 nano leads
Gemini 3.5 Flash Lite: 25.9 (#264), GPT-4.1 nano: 26.9 (#252)
| Benchmark | Gemini 3.5 Flash Lite | GPT-4.1 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 28.9% |
| LMArena Math | 1433 | 1274 |
| FrontierMath (Tiers 1-3) | 26% | — |
| FrontierMath Tier 4 | 0% | — |
| ProofBench | 13% | — |
| Omni-MATH | — | 36.7% |
| MATH Level 5 | — | 70% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 50.1 (#72), GPT-4.1 nano: 21.8 (#273)
| Benchmark | Gemini 3.5 Flash Lite | GPT-4.1 nano |
|---|---|---|
| GPQA Diamond | 83.3% | 48.9% |
| LMArena Expert | 1435 | 1272 |
| SimpleQA Verified | — | 6% |
| MMLU-Pro | — | 55% |
| GPQA (HELM) | — | 50.7% |
Multimodal Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 41.1 (#40), GPT-4.1 nano: 29.2 (#113)
| Benchmark | Gemini 3.5 Flash Lite | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | 1268 | 1063 |
Multilingual Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 53.5 (#63), GPT-4.1 nano: 41.6 (#205)
| Benchmark | Gemini 3.5 Flash Lite | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | 1427 | 1260 |
| LMArena Chinese | 1469 | 1270 |
| LMArena German | 1454 | 1288 |
| LMArena Japanese | 1427 | 1198 |
| LMArena Russian | 1443 | 1261 |
| LMArena French | 1451 | — |
| LMArena Korean | 1407 | — |
| LMArena Spanish | 1442 | — |
Instruction Following Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 74.8 (#85), GPT-4.1 nano: 67.8 (#193)
| Benchmark | Gemini 3.5 Flash Lite | GPT-4.1 nano |
|---|---|---|
| LMArena Instruction Following | 1420 | 1267 |
| IFEval | — | 84.3% |
Long Context Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 43.9 (#84), GPT-4.1 nano: 23.7 (#296)
| Benchmark | Gemini 3.5 Flash Lite | GPT-4.1 nano |
|---|---|---|
| LMArena Longer Query | 1435 | 1283 |
| Fiction.LiveBench | — | 25% |
Writing & Preference Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 64.2 (#57), GPT-4.1 nano: 40.5 (#243)
| Benchmark | Gemini 3.5 Flash Lite | GPT-4.1 nano |
|---|---|---|
| LMArena Text | 1435 | 1285 |
| LMArena Creative Writing | 1420 | 1260 |
| EQ-Bench Creative Writing | 1559 | 946 |
| LMArena Multi-Turn | 1445 | 1277 |
| WildBench | — | 81.2% |
Frequently asked questions
Is Gemini 3.5 Flash Lite better than GPT-4.1 nano?
Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 27.9 on the Noometry Index. GPT-4.1 nano costs 4.9× less per token, which makes it the better buy when Gemini 3.5 Flash Lite's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.5 Flash Lite or GPT-4.1 nano?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Gemini 3.5 Flash Lite lists at $0.30 and $2.50.
Is Gemini 3.5 Flash Lite or GPT-4.1 nano better for coding?
Gemini 3.5 Flash Lite scores higher on coding benchmarks: 42.4 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.5 Flash Lite does, with 1.05M tokens against 1.05M.
How many benchmarks do Gemini 3.5 Flash Lite and GPT-4.1 nano share?
26 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and GPT-4.1 nano has 38.