Model comparison
Gemini 1.5 Pro (May 2024) vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 49.2 to 31.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
GoogleSummary
- They share 13 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and GPT-6 Sol in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 49.3 to 12.3.
Side by side
| Gemini 1.5 Pro (May 2024) | GPT-6 Sol | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 31.9 | 49.2 |
| Released | 2024-02-15 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 45 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Gemini 1.5 Pro (May 2024): 33.8 (#239), GPT-6 Sol: 59.6 (#11)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1294 | 1453 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| LMArena WebDev | — | 1692 |
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use GPT-6 Sol leads
Gemini 1.5 Pro (May 2024): 17.8 (#137), GPT-6 Sol: 33.5 (#49)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-6 Sol |
|---|---|---|
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
| GDP.pdf | — | 28% |
Reasoning GPT-6 Sol leads
Gemini 1.5 Pro (May 2024): 12.3 (#332), GPT-6 Sol: 49.3 (#34)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1420 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| NYT Connections (extended) | — | 90.1% |
| EBR-Bench | — | 53.3% |
| DTBench | 59% | — |
| BIG-Bench Hard | 89.2% | — |
| Epoch Capabilities Index | 131.73 | — |
| ForecastBench | 58.4 | — |
Math GPT-6 Sol leads
Gemini 1.5 Pro (May 2024): 24.4 (#260), GPT-6 Sol: 35.8 (#135)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1315 | 1404 |
| OTIS Mock AIME 2024-2025 | 23.1% | — |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
Knowledge GPT-6 Sol leads
Gemini 1.5 Pro (May 2024): 29.3 (#228), GPT-6 Sol: 43.0 (#87)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Expert | 1279 | 1449 |
| GPQA Diamond | 57.2% | — |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| Vectara Hallucination Rate | — | 6.5% |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal GPT-6 Sol leads
Gemini 1.5 Pro (May 2024): 36.2 (#72), GPT-6 Sol: 47.6 (#9)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
| Furniture Assembly | — | 58.3% |
Multilingual GPT-6 Sol leads
Gemini 1.5 Pro (May 2024): 45.5 (#169), GPT-6 Sol: 51.0 (#113)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1312 | 1389 |
| LMArena Chinese | 1331 | 1416 |
| LMArena Russian | 1320 | 1407 |
| LMArena Spanish | 1310 | 1377 |
| LMArena French | 1301 | — |
| LMArena German | 1286 | — |
| LMArena Japanese | 1292 | — |
| LMArena Korean | 1298 | — |
Instruction Following GPT-6 Sol leads
Gemini 1.5 Pro (May 2024): 68.8 (#180), GPT-6 Sol: 74.4 (#97)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1297 | 1406 |
| IFEval | 83.7% | — |
Long Context GPT-6 Sol leads
Gemini 1.5 Pro (May 2024): 39.7 (#164), GPT-6 Sol: 43.2 (#100)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1308 | 1415 |
Writing & Preference GPT-6 Sol leads
Gemini 1.5 Pro (May 2024): 52.5 (#167), GPT-6 Sol: 72.3 (#15)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1319 | 1396 |
| LMArena Creative Writing | 1333 | 1392 |
| LMArena Multi-Turn | 1296 | 1405 |
| EQ-Bench Creative Writing | — | 2125 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 49.2 to 31.9 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 33.8 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and GPT-6 Sol share?
13 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and GPT-6 Sol has 22.