Model comparison
Gemini 2.0 Flash-Lite vs GPT-4.5
Gemini 2.0 Flash-Lite and GPT-4.5 score almost the same on the Noometry Index (37.8 vs 37.2), so choose on price, context window or the category you care about most.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Gemini 2.0 Flash-Lite scores higher in 3 categories and GPT-4.5 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 2.0 Flash-Lite leads 22.0 to 13.9.
- The biggest single-benchmark swing is LiveBench Coding: 47.1% for Gemini 2.0 Flash-Lite and 75.2% for GPT-4.5.
Side by side
| Gemini 2.0 Flash-Lite | GPT-4.5 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 37.8 | 37.2 |
| Released | 2025-02-05 | 2025-02-27 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
Gemini 2.0 Flash-Lite: 37.9 (#185), GPT-4.5: 42.2 (#109)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4.5 |
|---|---|---|
| LiveBench Coding | 47.1% | 75.2% |
| LMArena Coding | 1322 | 1396 |
| Aider Polyglot | — | 44.9% |
| WeirdML | — | 39.4% |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash-Lite: —, GPT-4.5: 27.9 (#97)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4.5 |
|---|---|---|
| Cybench | — | 17.5% |
Reasoning Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 22.0 (#210), GPT-4.5: 13.9 (#330)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4.5 |
|---|---|---|
| LiveBench Reasoning | 50.1% | 71.1% |
| LMArena Hard Prompts | 1324 | 1403 |
| LiveBench Data Analysis | 65.5% | 64.3% |
| ForecastBench | 57.1 | 61.7 |
| LiveBench | 54.3% | 69% |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 34.5% |
| ARC-AGI-1 | — | 10.3% |
| EnigmaEval | — | 3.2% |
| DTBench | 52.5% | — |
| Epoch Capabilities Index | — | 136.74 |
Math Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 34.1 (#196), GPT-4.5: 32.6 (#211)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4.5 |
|---|---|---|
| LiveBench Math | 58.1% | 69.3% |
| LMArena Math | 1309 | 1412 |
| OTIS Mock AIME 2024-2025 | — | 37.8% |
| Omni-MATH | 37.4% | — |
| MATH Level 5 | — | 78.6% |
Knowledge Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 35.0 (#189), GPT-4.5: 32.5 (#211)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4.5 |
|---|---|---|
| LMArena Expert | 1305 | 1394 |
| GPQA Diamond | — | 68.7% |
| Humanity's Last Exam | — | 5.4% |
| MMLU-Pro | 72% | — |
| Confabulations | — | 13.6% |
| GPQA (HELM) | 50% | — |
Multimodal GPT-4.5 leads
Gemini 2.0 Flash-Lite: 31.2 (#109), GPT-4.5: 37.6 (#71)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1100 | 1195 |
| VPCT | — | 45% |
Multilingual GPT-4.5 leads
Gemini 2.0 Flash-Lite: 46.0 (#161), GPT-4.5: 52.5 (#83)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1323 | 1413 |
| LMArena Chinese | 1339 | 1421 |
| LMArena French | 1347 | 1418 |
| LMArena German | 1306 | 1457 |
| LMArena Japanese | 1301 | 1416 |
| LMArena Korean | 1325 | 1392 |
| LMArena Russian | 1328 | 1419 |
| LMArena Spanish | 1313 | — |
Instruction Following GPT-4.5 leads
Gemini 2.0 Flash-Lite: 70.4 (#163), GPT-4.5: 72.6 (#134)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4.5 |
|---|---|---|
| LiveBench Instruction Following | 78.3% | 72.3% |
| LMArena Instruction Following | 1305 | 1404 |
| IFEval | 82.4% | — |
Long Context Too close to call
Gemini 2.0 Flash-Lite: 40.1 (#160), GPT-4.5: 40.4 (#155)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1320 | 1406 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference GPT-4.5 leads
Gemini 2.0 Flash-Lite: 51.7 (#177), GPT-4.5: 56.9 (#134)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4.5 |
|---|---|---|
| LMArena Text | 1330 | 1417 |
| LMArena Creative Writing | 1319 | 1394 |
| LMArena Multi-Turn | 1307 | 1444 |
| LiveBench Language | 34.3% | 61.5% |
| Short-Story Creative Writing | — | 75.6% |
| EQ-Bench Creative Writing | — | 1258 |
| WildBench | 79% | — |
Frequently asked questions
Is Gemini 2.0 Flash-Lite better than GPT-4.5?
Gemini 2.0 Flash-Lite and GPT-4.5 score almost the same on the Noometry Index (37.8 vs 37.2), so choose on price, context window or the category you care about most.
Is Gemini 2.0 Flash-Lite or GPT-4.5 better for coding?
GPT-4.5 scores higher on coding benchmarks: 42.2 versus 37.9 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash-Lite and GPT-4.5 share?
25 benchmarks have published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and GPT-4.5 has 42.