Model comparison
Gemini 1.5 Pro (May 2024) vs GPT-5
GPT-5 is the stronger model overall, scoring 50.9 to 32.1 on the Noometry Index.
Last verified . 35 shared benchmarks.
GoogleSummary
- They share 35 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and GPT-5 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 39.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 91.4% for GPT-5.
Side by side
| Gemini 1.5 Pro (May 2024) | GPT-5 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 32.1 | 50.9 |
| Released | 2024-02-15 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 45 | 69 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), GPT-5: 50.3 (#47)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 |
|---|---|---|
| WeirdML | 22.2% | 60.7% |
| LMArena Coding | 1294 | 1436 |
| SWE-bench Verified | — | 73.6% |
| SWE-bench Verified (bash only) | — | 65% |
| Aider Polyglot | — | 88% |
| LMArena WebDev | — | 1418 |
| SciCode | — | 42.9% |
| GSO | — | 6.9% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| ALE-Bench | — | 1,162 |
| AlgoTune | — | 1.67 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use GPT-5 leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), GPT-5: 33.1 (#56)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 |
|---|---|---|
| BALROG | 21% | 32.8% |
| Terminal-Bench | — | 49.6% |
| GDPval | — | 34.8% |
| Remote Labor Index | — | 1.7% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| DeepResearch Bench | — | 49.6% |
| LMArena Search | — | 1133 |
| METR Time Horizons | — | 69.6% |
Reasoning GPT-5 leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), GPT-5: 38.3 (#64)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 |
|---|---|---|
| ARC-AGI-2 | 0.8% | 9.9% |
| SimpleBench | 27.1% | 56.7% |
| LMArena Hard Prompts | 1296 | 1416 |
| DTBench | 59% | 90.7% |
| Epoch Capabilities Index | 131.73 | 150 |
| ForecastBench | 58.4 | 61.4 |
| Kagi LLM Benchmark | — | 72.7% |
| ARC-AGI-1 | — | 65.7% |
| CritPt | — | 12.6% |
| Chess Puzzles | — | 37% |
| EnigmaEval | — | 10.5% |
| EBR-Bench | — | 12.7% |
| Mystery Game Puzzles | — | 23% |
| LMCA | — | 40% |
| BIG-Bench Hard | 89.2% | — |
Math GPT-5 leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), GPT-5: 55.0 (#44)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 91.4% |
| Omni-MATH | 36.4% | 64.7% |
| LMArena Math | 1315 | 1407 |
| MATH Level 5 | 70.4% | 98.1% |
| FrontierMath (Tiers 1-3) | — | 55.4% |
| FrontierMath Tier 4 | — | 22% |
| ProofBench | — | 18% |
| FrontierMath (Feb 2025 set) | — | 32.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge GPT-5 leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), GPT-5: 56.6 (#43)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 |
|---|---|---|
| GPQA Diamond | 57.2% | 86.2% |
| Humanity's Last Exam | 4.6% | 25.3% |
| MMLU-Pro | 73.7% | 86.3% |
| Confabulations | 13.5% | 10.3% |
| GPQA (HELM) | 53.4% | 79.2% |
| LMArena Expert | 1279 | 1419 |
| SimpleQA Verified | — | 50.1% |
| Vectara Hallucination Rate | — | 14.7% |
| MMLU | 86.9% | — |
Multimodal GPT-5 leads
Gemini 1.5 Pro (May 2024): 36.8 (#77), GPT-5: 46.8 (#13)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 |
|---|---|---|
| LMArena Vision | 1161 | 1232 |
| Video-MME | 75% | — |
| GeoBench | — | 81% |
| VPCT | — | 66% |
Multilingual GPT-5 leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), GPT-5: 51.4 (#110)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 |
|---|---|---|
| LMArena Non-English | 1312 | 1397 |
| LMArena Chinese | 1331 | 1422 |
| LMArena French | 1302 | 1410 |
| LMArena German | 1286 | 1416 |
| LMArena Japanese | 1292 | 1409 |
| LMArena Korean | 1298 | 1360 |
| LMArena Russian | 1320 | 1406 |
| LMArena Spanish | 1311 | 1399 |
Instruction Following GPT-5 leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), GPT-5: 73.8 (#113)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 |
|---|---|---|
| IFEval | 83.7% | 87.5% |
| LMArena Instruction Following | 1297 | 1388 |
Long Context GPT-5 leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), GPT-5: 69.5 (#2)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 |
|---|---|---|
| LMArena Longer Query | 1308 | 1399 |
| Fiction.LiveBench | — | 97.2% |
Writing & Preference GPT-5 leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), GPT-5: 63.4 (#65)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 |
|---|---|---|
| LMArena Text | 1319 | 1406 |
| LMArena Creative Writing | 1333 | 1365 |
| WildBench | 81.3% | 85.7% |
| LMArena Multi-Turn | 1296 | 1426 |
| Short-Story Creative Writing | — | 86% |
| EQ-Bench Creative Writing | — | 1627 |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than GPT-5?
GPT-5 is the stronger model overall, scoring 50.9 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or GPT-5 better for coding?
GPT-5 scores higher on coding benchmarks: 50.3 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and GPT-5 share?
35 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and GPT-5 has 69.