Model comparison
Gemini 1.5 Pro (May 2024) vs GPT-5.2
GPT-5.2 is the stronger model overall, scoring 54.1 to 32.1 on the Noometry Index.
Last verified . 27 shared benchmarks.
GoogleSummary
- They share 27 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and GPT-5.2 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.2 leads 50.2 to 12.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 96.1% for GPT-5.2.
Side by side
| Gemini 1.5 Pro (May 2024) | GPT-5.2 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 32.1 | 54.1 |
| Released | 2024-02-15 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.75 |
| Output $ / M tokens | — | $14 |
| Results tracked | 45 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), GPT-5.2: 51.6 (#37)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.2 |
|---|---|---|
| WeirdML | 22.2% | 72.2% |
| LMArena Coding | 1294 | 1447 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1416 |
| SWE-bench Multilingual | — | 66.7% |
| GSO | — | 27.4% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| ALE-Bench | — | 1,294 |
| AlgoTune | — | 2.05 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use GPT-5.2 leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), GPT-5.2: 40.2 (#24)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.2 |
|---|---|---|
| Terminal-Bench | — | 64.9% |
| Berkeley Function Calling Leaderboard | — | 55.9% |
| GDPval | — | 49.7% |
| Remote Labor Index | — | 2.5% |
| TheAgentCompany | 3.4% | — |
| τ²-bench Airline | — | 83% |
| τ²-bench Banking | — | 32.2% |
| τ²-bench Retail | — | 81.6% |
| τ²-bench Telecom | — | 89.7% |
| Cybench | 7.5% | — |
| DeepResearch Bench | — | 41.1% |
| BALROG | 21% | — |
| LMArena Search | — | 1207 |
| METR Time Horizons | — | 75.3% |
| Vending-Bench 2 | — | 3,591 |
Reasoning GPT-5.2 leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), GPT-5.2: 50.2 (#35)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.2 |
|---|---|---|
| ARC-AGI-2 | 0.8% | 52.9% |
| SimpleBench | 27.1% | 45.8% |
| LMArena Hard Prompts | 1296 | 1445 |
| DTBench | 59% | 90.9% |
| Epoch Capabilities Index | 131.73 | 153.45 |
| ForecastBench | 58.4 | 60.1 |
| Kagi LLM Benchmark | — | 73.3% |
| NYT Connections (extended) | — | 83.6% |
| ARC-AGI-1 | — | 86.2% |
| Chess Puzzles | — | 49% |
| EnigmaEval | — | 10.4% |
| EBR-Bench | — | 23% |
| Mystery Game Puzzles | — | 23% |
| LMCA | — | 43.9% |
| BIG-Bench Hard | 89.2% | — |
Math GPT-5.2 leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), GPT-5.2: 60.0 (#38)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 96.1% |
| LMArena Math | 1315 | 1440 |
| FrontierMath (Tiers 1-3) | — | 67.4% |
| FrontierMath Tier 4 | — | 31.7% |
| MathArena Final-Answer Competitions | — | 72% |
| ProofBench | — | 15% |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
| FrontierMath (Feb 2025 set) | — | 40.7% |
| FrontierMath Tier 4 (v1) | — | 18.8% |
Knowledge GPT-5.2 leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), GPT-5.2: 59.3 (#32)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.2 |
|---|---|---|
| GPQA Diamond | 57.2% | 91.4% |
| Humanity's Last Exam | 4.6% | 27.8% |
| LMArena Expert | 1279 | 1445 |
| SimpleQA Verified | — | 37.1% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| Vectara Hallucination Rate | — | 8.4% |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal GPT-5.2 leads
Gemini 1.5 Pro (May 2024): 36.8 (#77), GPT-5.2: 51.3 (#7)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.2 |
|---|---|---|
| LMArena Vision | 1161 | 1268 |
| Video-MME | 75% | — |
| VPCT | — | 84% |
| Furniture Assembly | — | 38.3% |
| LMArena Document | — | 1405 |
Multilingual GPT-5.2 leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), GPT-5.2: 53.4 (#67)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1312 | 1425 |
| LMArena Chinese | 1331 | 1460 |
| LMArena French | 1302 | 1455 |
| LMArena German | 1286 | 1448 |
| LMArena Japanese | 1292 | 1420 |
| LMArena Korean | 1298 | 1392 |
| LMArena Russian | 1320 | 1440 |
| LMArena Spanish | 1311 | 1433 |
Instruction Following GPT-5.2 leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), GPT-5.2: 74.7 (#89)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1417 |
| IFEval | 83.7% | — |
Long Context GPT-5.2 leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), GPT-5.2: 44.0 (#78)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1308 | 1428 |
| CL-bench | — | 18.2% |
Writing & Preference GPT-5.2 leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), GPT-5.2: 66.8 (#32)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.2 |
|---|---|---|
| LMArena Text | 1319 | 1439 |
| LMArena Creative Writing | 1333 | 1401 |
| LMArena Multi-Turn | 1296 | 1458 |
| EQ-Bench Creative Writing | — | 1703 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than GPT-5.2?
GPT-5.2 is the stronger model overall, scoring 54.1 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or GPT-5.2 better for coding?
GPT-5.2 scores higher on coding benchmarks: 51.6 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and GPT-5.2 share?
27 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and GPT-5.2 has 67.