Model comparison
Gemini 1.5 Pro (May 2024) vs GPT-4.5
GPT-4.5 is the stronger model overall, scoring 37.2 to 32.1 on the Noometry Index.
Last verified . 28 shared benchmarks.
GoogleSummary
- They share 28 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and GPT-4.5 in 10 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-4.5 leads 27.9 to 17.9.
- The biggest single-benchmark swing is WeirdML: 22.2% for Gemini 1.5 Pro (May 2024) and 39.4% for GPT-4.5.
Side by side
| Gemini 1.5 Pro (May 2024) | GPT-4.5 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 32.1 | 37.2 |
| Released | 2024-02-15 | 2025-02-27 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 45 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), GPT-4.5: 42.2 (#109)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.5 |
|---|---|---|
| WeirdML | 22.2% | 39.4% |
| LMArena Coding | 1294 | 1396 |
| Aider Polyglot | — | 44.9% |
| BigCodeBench Instruct | 43.8% | — |
| LiveBench Coding | — | 75.2% |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use GPT-4.5 leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), GPT-4.5: 27.9 (#97)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.5 |
|---|---|---|
| Cybench | 7.5% | 17.5% |
| TheAgentCompany | 3.4% | — |
| BALROG | 21% | — |
Reasoning GPT-4.5 leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), GPT-4.5: 13.9 (#330)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.5 |
|---|---|---|
| ARC-AGI-2 | 0.8% | 0.8% |
| SimpleBench | 27.1% | 34.5% |
| LMArena Hard Prompts | 1296 | 1403 |
| Epoch Capabilities Index | 131.73 | 136.74 |
| ForecastBench | 58.4 | 61.7 |
| ARC-AGI-1 | — | 10.3% |
| EnigmaEval | — | 3.2% |
| LiveBench Reasoning | — | 71.1% |
| DTBench | 59% | — |
| LiveBench Data Analysis | — | 64.3% |
| BIG-Bench Hard | 89.2% | — |
| LiveBench | — | 69% |
Math GPT-4.5 leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), GPT-4.5: 32.6 (#211)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 37.8% |
| LMArena Math | 1315 | 1412 |
| MATH Level 5 | 70.4% | 78.6% |
| Omni-MATH | 36.4% | — |
| LiveBench Math | — | 69.3% |
Knowledge GPT-4.5 leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), GPT-4.5: 32.5 (#211)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.5 |
|---|---|---|
| GPQA Diamond | 57.2% | 68.7% |
| Humanity's Last Exam | 4.6% | 5.4% |
| Confabulations | 13.5% | 13.6% |
| LMArena Expert | 1279 | 1394 |
| MMLU-Pro | 73.7% | — |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal Too close to call
Gemini 1.5 Pro (May 2024): 36.8 (#77), GPT-4.5: 37.6 (#71)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1161 | 1195 |
| Video-MME | 75% | — |
| VPCT | — | 45% |
Multilingual GPT-4.5 leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), GPT-4.5: 52.5 (#83)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1312 | 1413 |
| LMArena Chinese | 1331 | 1421 |
| LMArena French | 1302 | 1418 |
| LMArena German | 1286 | 1457 |
| LMArena Japanese | 1292 | 1416 |
| LMArena Korean | 1298 | 1392 |
| LMArena Russian | 1320 | 1419 |
| LMArena Spanish | 1311 | — |
Instruction Following GPT-4.5 leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), GPT-4.5: 72.6 (#134)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1404 |
| LiveBench Instruction Following | — | 72.3% |
| IFEval | 83.7% | — |
Long Context Too close to call
Gemini 1.5 Pro (May 2024): 39.8 (#169), GPT-4.5: 40.4 (#155)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1308 | 1406 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference GPT-4.5 leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), GPT-4.5: 56.9 (#134)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.5 |
|---|---|---|
| LMArena Text | 1319 | 1417 |
| LMArena Creative Writing | 1333 | 1394 |
| LMArena Multi-Turn | 1296 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| EQ-Bench Creative Writing | — | 1258 |
| WildBench | 81.3% | — |
| LiveBench Language | — | 61.5% |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than GPT-4.5?
GPT-4.5 is the stronger model overall, scoring 37.2 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or GPT-4.5 better for coding?
GPT-4.5 scores higher on coding benchmarks: 42.2 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and GPT-4.5 share?
28 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and GPT-4.5 has 42.