Model comparison
Gemini 2.5 Pro vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 49.2 to 44.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
GoogleSummary
- They share 16 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 4 categories and GPT-6 Sol in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 49.3 to 28.8.
- Gemini 2.5 Pro is cheaper at $1.25 / $10 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 1.05M.
Side by side
| Gemini 2.5 Pro | GPT-6 Sol | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 44.9 | 49.2 |
| Released | 2025-03-25 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 128K |
| Input $ / M tokens | $1.25 | $2 |
| Output $ / M tokens | $10 | $10 |
| Results tracked | 78 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Gemini 2.5 Pro: 42.8 (#86), GPT-6 Sol: 59.6 (#11)
| Benchmark | Gemini 2.5 Pro | GPT-6 Sol |
|---|---|---|
| LMArena WebDev | 1227 | 1692 |
| LMArena Coding | 1452 | 1453 |
| SWE-bench Verified | 57.6% | — |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| SciCode | 42.8% | — |
| GSO | 3.9% | — |
| WeirdML | 54% | — |
| LiveBench Coding | 85.9% | — |
| CadEval | 64% | — |
| ALE-Bench | 785.52 | — |
| AlgoTune | 1.51 | — |
Agentic & Tool Use GPT-6 Sol leads
Gemini 2.5 Pro: 29.1 (#81), GPT-6 Sol: 33.5 (#49)
| Benchmark | Gemini 2.5 Pro | GPT-6 Sol |
|---|---|---|
| Terminal-Bench | 32.6% | — |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| GDP.pdf | — | 28% |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |
| Vending-Bench 2 | 573.64 | — |
Reasoning GPT-6 Sol leads
Gemini 2.5 Pro: 28.8 (#85), GPT-6 Sol: 49.3 (#34)
| Benchmark | Gemini 2.5 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 1455 | 1420 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 62.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | 41% | — |
| CritPt | 2% | — |
| Chess Puzzles | 20% | — |
| EnigmaEval | 5.6% | — |
| EBR-Bench | — | 53.3% |
| LiveBench Reasoning | 89.8% | — |
| DTBench | 82.4% | — |
| LiveBench Data Analysis | 79.9% | — |
| LMCA | 34.8% | — |
| Epoch Capabilities Index | 145.32 | — |
| ForecastBench | 61.3 | — |
| LiveBench | 82.3% | — |
Math GPT-6 Sol leads
Gemini 2.5 Pro: 31.9 (#191), GPT-6 Sol: 35.8 (#135)
| Benchmark | Gemini 2.5 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1450 | 1404 |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 84.7% | — |
| Omni-MATH | 41.6% | — |
| LiveBench Math | 90.2% | — |
| MATH Level 5 | 95.9% | — |
| FrontierMath (Feb 2025 set) | 14.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 2.5 Pro leads
Gemini 2.5 Pro: 55.8 (#41), GPT-6 Sol: 43.0 (#87)
| Benchmark | Gemini 2.5 Pro | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | 7% | 6.5% |
| LMArena Expert | 1452 | 1449 |
| GPQA Diamond | 85.3% | — |
| Humanity's Last Exam | 21.6% | — |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.6% | — |
| GPQA (HELM) | 74.9% | — |
Multimodal GPT-6 Sol leads
Gemini 2.5 Pro: 44.5 (#16), GPT-6 Sol: 47.6 (#9)
| Benchmark | Gemini 2.5 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1263 | — |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| Furniture Assembly | — | 58.3% |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |
Multilingual Gemini 2.5 Pro leads
Gemini 2.5 Pro: 55.5 (#30), GPT-6 Sol: 51.0 (#113)
| Benchmark | Gemini 2.5 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1452 | 1389 |
| LMArena Chinese | 1507 | 1416 |
| LMArena Russian | 1460 | 1407 |
| LMArena Spanish | 1473 | 1377 |
| LMArena French | 1473 | — |
| LMArena German | 1487 | — |
| LMArena Japanese | 1462 | — |
| LMArena Korean | 1435 | — |
Instruction Following Too close to call
Gemini 2.5 Pro: 75.2 (#71), GPT-6 Sol: 74.4 (#97)
| Benchmark | Gemini 2.5 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1436 | 1406 |
| LiveBench Instruction Following | 80.6% | — |
| IFEval | 84% | — |
Long Context Gemini 2.5 Pro leads
Gemini 2.5 Pro: 59.7 (#5), GPT-6 Sol: 43.2 (#100)
| Benchmark | Gemini 2.5 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1449 | 1415 |
| Fiction.LiveBench | 91.7% | — |
Writing & Preference GPT-6 Sol leads
Gemini 2.5 Pro: 63.9 (#60), GPT-6 Sol: 72.3 (#15)
| Benchmark | Gemini 2.5 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1458 | 1396 |
| LMArena Creative Writing | 1453 | 1392 |
| EQ-Bench Creative Writing | 1421 | 2125 |
| LMArena Multi-Turn | 1453 | 1405 |
| Short-Story Creative Writing | 83.8% | — |
| WildBench | 85.7% | — |
| LiveBench Language | 67.8% | — |
Frequently asked questions
Is Gemini 2.5 Pro better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 49.2 to 44.9 on the Noometry Index.
Which is cheaper, Gemini 2.5 Pro or GPT-6 Sol?
Gemini 2.5 Pro is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is Gemini 2.5 Pro or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 42.8 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 1.05M.
How many benchmarks do Gemini 2.5 Pro and GPT-6 Sol share?
16 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and GPT-6 Sol has 22.