Model comparison
Gemini 2.0 Flash (Feb 2025) vs GPT-4.5
GPT-4.5 is the stronger model overall, scoring 36.9 to 34.8 on the Noometry Index.
Last verified . 38 shared benchmarks.
GoogleSummary
- They share 38 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 4 categories and GPT-4.5 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-4.5 leads 41.8 to 28.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Gemini 2.0 Flash (Feb 2025) and 37.8% for GPT-4.5.
Side by side
| Gemini 2.0 Flash (Feb 2025) | GPT-4.5 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 34.8 | 36.9 |
| Released | 2024-12-06 | 2025-02-27 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 54 | 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 (Feb 2025): 28.2 (#308), GPT-4.5: 41.8 (#102)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.5 |
|---|---|---|
| Aider Polyglot | 38.2% | 44.9% |
| WeirdML | 25.8% | 39.4% |
| LiveBench Coding | 63.4% | 75.2% |
| LMArena Coding | 1351 | 1397 |
| SWE-bench Verified (bash only) | 13.5% | — |
| BigCodeBench Instruct | 45.9% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
Agentic & Tool Use Too close to call
Gemini 2.0 Flash (Feb 2025): 28.0 (#85), GPT-4.5: 27.6 (#92)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.5 |
|---|---|---|
| TheAgentCompany | 11.4% | — |
| Cybench | — | 17.5% |
Reasoning Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#308), GPT-4.5: 14.1 (#320)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.5 |
|---|---|---|
| ARC-AGI-2 | 1.3% | 0.8% |
| SimpleBench | 31.1% | 34.5% |
| EnigmaEval | 1.1% | 3.2% |
| LiveBench Reasoning | 78.2% | 71.1% |
| LMArena Hard Prompts | 1346 | 1404 |
| LiveBench Data Analysis | 69.4% | 64.3% |
| Epoch Capabilities Index | 135.36 | 136.74 |
| LiveBench | 66.9% | 69% |
| Kagi LLM Benchmark | 37.8% | — |
| ARC-AGI-1 | — | 10.3% |
| DTBench | 63.2% | — |
| ForecastBench | — | 61.7 |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 36.1 (#127), GPT-4.5: 31.0 (#200)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 37.8% |
| LiveBench Math | 75.8% | 69.3% |
| LMArena Math | 1351 | 1412 |
| MATH Level 5 | 82.2% | 78.6% |
| Omni-MATH | 45.9% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Too close to call
Gemini 2.0 Flash (Feb 2025): 32.0 (#207), GPT-4.5: 32.4 (#205)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.5 |
|---|---|---|
| GPQA Diamond | 64.1% | 68.7% |
| Humanity's Last Exam | 6.6% | 5.4% |
| Confabulations | 12.4% | 13.6% |
| LMArena Expert | 1340 | 1394 |
| MMLU-Pro | 73.7% | — |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal GPT-4.5 leads
Gemini 2.0 Flash (Feb 2025): 35.9 (#74), GPT-4.5: 37.0 (#68)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1158 | 1195 |
| GeoBench | 77% | — |
| VPCT | — | 45% |
Multilingual GPT-4.5 leads
Gemini 2.0 Flash (Feb 2025): 47.6 (#144), GPT-4.5: 52.7 (#78)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1342 | 1413 |
| LMArena Chinese | 1373 | 1421 |
| LMArena French | 1390 | 1417 |
| LMArena German | 1354 | 1457 |
| LMArena Japanese | 1293 | 1416 |
| LMArena Korean | 1314 | 1392 |
| LMArena Russian | 1351 | 1419 |
| LMArena Spanish | 1363 | — |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.6 (#91), GPT-4.5: 72.8 (#129)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.5 |
|---|---|---|
| LiveBench Instruction Following | 85.8% | 72.3% |
| LMArena Instruction Following | 1336 | 1404 |
| IFEval | 84.1% | — |
Long Context GPT-4.5 leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#198), GPT-4.5: 40.4 (#150)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.5 |
|---|---|---|
| Fiction.LiveBench | 61.1% | 63.9% |
| LMArena Longer Query | 1345 | 1406 |
Writing & Preference GPT-4.5 leads
Gemini 2.0 Flash (Feb 2025): 49.8 (#184), GPT-4.5: 57.1 (#129)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.5 |
|---|---|---|
| LMArena Text | 1354 | 1417 |
| LMArena Creative Writing | 1340 | 1394 |
| Short-Story Creative Writing | 73.8% | 75.6% |
| EQ-Bench Creative Writing | 1128 | 1258 |
| LMArena Multi-Turn | 1350 | 1444 |
| LiveBench Language | 51.3% | 61.5% |
| WildBench | 80% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than GPT-4.5?
GPT-4.5 is the stronger model overall, scoring 36.9 to 34.8 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or GPT-4.5 better for coding?
GPT-4.5 scores higher on coding benchmarks: 41.8 versus 28.2 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and GPT-4.5 share?
38 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and GPT-4.5 has 42.