Model comparison
Gemini 3.5 Flash Lite vs GPT-5.2 Pro
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 41.5 on the Noometry Index. Gemini 3.5 Flash Lite costs 68× less per token, which makes it the better buy when GPT-5.2 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-5.2 Pro in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.2 Pro leads 65.3 to 25.9.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 26% for Gemini 3.5 Flash Lite and 74% for GPT-5.2 Pro.
- Gemini 3.5 Flash Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
- Gemini 3.5 Flash Lite accepts more context: 1.05M tokens versus 400K.
Side by side
| Gemini 3.5 Flash Lite | GPT-5.2 Pro | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 41.5 | 52.3 |
| Released | 2026-07-21 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.30 | $21 |
| Output $ / M tokens | $2.50 | $168 |
| Results tracked | 39 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemini 3.5 Flash Lite: 42.4 (#104), GPT-5.2 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5.2 Pro |
|---|---|---|
| LMArena WebDev | 1440 | — |
| SciCode | 41.3% | — |
| WeirdML | 39% | — |
| LMArena Coding | 1453 | — |
| ALE-Bench | 765.27 | — |
Agentic & Tool Use Not comparable
Gemini 3.5 Flash Lite: 25.7 (#107), GPT-5.2 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5.2 Pro |
|---|---|---|
| APEX-Agents | 29.3% | — |
| GDP.pdf | 10% | — |
Reasoning GPT-5.2 Pro leads
Gemini 3.5 Flash Lite: 27.8 (#114), GPT-5.2 Pro: 51.5 (#33)
| Benchmark | Gemini 3.5 Flash Lite | GPT-5.2 Pro |
|---|---|---|
| ARC-AGI-2 | 10.3% | 54.2% |
| NYT Connections (extended) | 60.4% | 79.3% |
| ARC-AGI-1 | 53.5% | 90.5% |
| Epoch Capabilities Index | 145.13 | 155.4 |
| SimpleBench | — | 57.4% |
| CritPt | 0% | — |
| Chess Puzzles | 22% | — |
| LMArena Hard Prompts | 1441 | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 83.5% | — |
| LMCA | 37.6% | — |
Math GPT-5.2 Pro leads
Gemini 3.5 Flash Lite: 25.9 (#264), GPT-5.2 Pro: 65.3 (#29)
| Benchmark | Gemini 3.5 Flash Lite | GPT-5.2 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 26% | 74% |
| FrontierMath Tier 4 | 0% | 46% |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 13% | — |
| LMArena Math | 1433 | — |
| FrontierMath Tier 4 (v1) | — | 31.3% |
Knowledge Not comparable
Gemini 3.5 Flash Lite: 50.1 (#72), GPT-5.2 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5.2 Pro |
|---|---|---|
| GPQA Diamond | 83.3% | — |
| LMArena Expert | 1435 | — |
Multimodal Not comparable
Gemini 3.5 Flash Lite: 41.1 (#40), GPT-5.2 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5.2 Pro |
|---|---|---|
| LMArena Vision | 1268 | — |
Multilingual Not comparable
Gemini 3.5 Flash Lite: 53.5 (#63), GPT-5.2 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5.2 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-5.2 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5.2 Pro |
|---|---|---|
| LMArena Instruction Following | 1420 | — |
Long Context Not comparable
Gemini 3.5 Flash Lite: 43.9 (#84), GPT-5.2 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5.2 Pro |
|---|---|---|
| LMArena Longer Query | 1435 | — |
Writing & Preference Not comparable
Gemini 3.5 Flash Lite: 64.2 (#57), GPT-5.2 Pro: —
| Benchmark | Gemini 3.5 Flash Lite | GPT-5.2 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-5.2 Pro?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 41.5 on the Noometry Index. Gemini 3.5 Flash Lite costs 68× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.5 Flash Lite or GPT-5.2 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-5.2 Pro lists at $21 and $168.
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-5.2 Pro share?
6 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and GPT-5.2 Pro has 8.