Model comparison
Gemini 3.5 Flash Lite vs GPT-5 Pro
GPT-5 Pro is the stronger model overall, scoring 46.4 to 41.5 on the Noometry Index. Gemini 3.5 Flash Lite costs 49× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
GoogleSummary
- They share 6 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 0 categories and GPT-5 Pro in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Pro leads 48.5 to 25.9.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 26% for Gemini 3.5 Flash Lite and 55.8% for GPT-5 Pro.
- Gemini 3.5 Flash Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
- Gemini 3.5 Flash Lite accepts more context: 1.05M tokens versus 400K.
Side by side
| Gemini 3.5 Flash Lite | GPT-5 Pro | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 41.5 | 46.4 |
| Released | 2026-07-21 | 2025-10-06 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 66K | 272K |
| Input $ / M tokens | $0.30 | $15 |
| Output $ / M tokens | $2.50 | $120 |
| Results tracked | 39 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Pro leads
Gemini 3.5 Flash Lite: 42.4 (#104), GPT-5 Pro: 44.0 (#80)
| Benchmark | Gemini 3.5 Flash Lite | GPT-5 Pro |
|---|---|---|
| WeirdML | 39% | 60.4% |
| LMArena WebDev | 1440 | — |
| SciCode | 41.3% | — |
| LMArena Coding | 1453 | — |
| ALE-Bench | 765.27 | — |
| AlgoTune | — | 1.31 |
Agentic & Tool Use Not comparable
Gemini 3.5 Flash Lite: 25.7 (#107), GPT-5 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5 Pro |
|---|---|---|
| APEX-Agents | 29.3% | — |
| GDP.pdf | 10% | — |
Reasoning GPT-5 Pro leads
Gemini 3.5 Flash Lite: 27.8 (#114), GPT-5 Pro: 38.9 (#62)
| Benchmark | Gemini 3.5 Flash Lite | GPT-5 Pro |
|---|---|---|
| ARC-AGI-2 | 10.3% | 18.3% |
| ARC-AGI-1 | 53.5% | 70.2% |
| Epoch Capabilities Index | 145.13 | 150.28 |
| SimpleBench | — | 61.6% |
| Kagi LLM Benchmark | — | 76.8% |
| NYT Connections (extended) | 60.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 22% | — |
| EnigmaEval | — | 18.8% |
| LMArena Hard Prompts | 1441 | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 83.5% | — |
| LMCA | 37.6% | — |
Math GPT-5 Pro leads
Gemini 3.5 Flash Lite: 25.9 (#264), GPT-5 Pro: 48.5 (#63)
| Benchmark | Gemini 3.5 Flash Lite | GPT-5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 26% | 55.8% |
| FrontierMath Tier 4 | 0% | 19.5% |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 13% | — |
| LMArena Math | 1433 | — |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge GPT-5 Pro leads
Gemini 3.5 Flash Lite: 50.1 (#72), GPT-5 Pro: 56.7 (#42)
| Benchmark | Gemini 3.5 Flash Lite | GPT-5 Pro |
|---|---|---|
| GPQA Diamond | 83.3% | — |
| Humanity's Last Exam | — | 31.6% |
| LMArena Expert | 1435 | — |
Multimodal Not comparable
Gemini 3.5 Flash Lite: 41.1 (#40), GPT-5 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5 Pro |
|---|---|---|
| LMArena Vision | 1268 | — |
Multilingual Not comparable
Gemini 3.5 Flash Lite: 53.5 (#63), GPT-5 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5 Pro |
|---|---|---|
| LMArena Non-English | 1427 | — |
| LMArena Chinese | 1469 | — |
| LMArena French | 1451 | — |
| LMArena German | 1454 | — |
| LMArena Japanese | 1427 | — |
| LMArena Korean | 1407 | — |
| LMArena Russian | 1443 | — |
| LMArena Spanish | 1442 | — |
Instruction Following Not comparable
Gemini 3.5 Flash Lite: 74.8 (#85), GPT-5 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5 Pro |
|---|---|---|
| LMArena Instruction Following | 1420 | — |
Long Context Not comparable
Gemini 3.5 Flash Lite: 43.9 (#84), GPT-5 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5 Pro |
|---|---|---|
| LMArena Longer Query | 1435 | — |
Writing & Preference Not comparable
Gemini 3.5 Flash Lite: 64.2 (#57), GPT-5 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5 Pro |
|---|---|---|
| LMArena Text | 1435 | — |
| LMArena Creative Writing | 1420 | — |
| EQ-Bench Creative Writing | 1559 | — |
| LMArena Multi-Turn | 1445 | — |
Frequently asked questions
Is Gemini 3.5 Flash Lite better than GPT-5 Pro?
GPT-5 Pro is the stronger model overall, scoring 46.4 to 41.5 on the Noometry Index. Gemini 3.5 Flash Lite costs 49× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.5 Flash Lite or GPT-5 Pro?
Gemini 3.5 Flash Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; GPT-5 Pro lists at $15 and $120.
Is Gemini 3.5 Flash Lite or GPT-5 Pro better for coding?
GPT-5 Pro scores higher on coding benchmarks: 44.0 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.5 Flash Lite does, with 1.05M tokens against 400K.
How many benchmarks do Gemini 3.5 Flash Lite and GPT-5 Pro share?
6 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and GPT-5 Pro has 12.