Model comparison
Gemini 2.5 Flash vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 4.7× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
GoogleSummary
- They share 29 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 3 categories and GPT-6 Sol in 7 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 18.1.
- The biggest single-benchmark swing is ARC-AGI-2: 2.5% for Gemini 2.5 Flash and 89.6% for GPT-6 Sol.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 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 Flash | GPT-6 Sol | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 39.3 | 61.8 |
| Released | 2025-04-17 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.30 | $2 |
| Output $ / M tokens | $2.50 | $10 |
| Results tracked | 54 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Gemini 2.5 Flash: 35.8 (#220), GPT-6 Sol: 60.1 (#11)
| Benchmark | Gemini 2.5 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1424 | 1447 |
| ALE-Bench | 661.88 | 2,462 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1688 |
| SciCode | — | 57.6% |
| WeirdML | 41.9% | — |
Agentic & Tool Use GPT-6 Sol leads
Gemini 2.5 Flash: 30.8 (#74), GPT-6 Sol: 37.2 (#36)
| Benchmark | Gemini 2.5 Flash | GPT-6 Sol |
|---|---|---|
| Vending-Bench 2 | 548.84 | 14,428 |
| Terminal-Bench | 17.1% | — |
| APEX-Agents | — | 54.3% |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| GDP.pdf | — | 26.4% |
Reasoning GPT-6 Sol leads
Gemini 2.5 Flash: 18.1 (#286), GPT-6 Sol: 74.0 (#9)
| Benchmark | Gemini 2.5 Flash | GPT-6 Sol |
|---|---|---|
| ARC-AGI-2 | 2.5% | 89.6% |
| ARC-AGI-1 | 33.3% | 95.5% |
| CritPt | 1.1% | 30.9% |
| LMArena Hard Prompts | 1422 | 1418 |
| DTBench | 76.5% | 97.3% |
| LMCA | 27.5% | 59.1% |
| Epoch Capabilities Index | 143.03 | 162.72 |
| SimpleBench | 41.2% | — |
| Kagi LLM Benchmark | 56.8% | — |
| NYT Connections (extended) | — | 90.1% |
| EnigmaEval | 2.7% | — |
| EBR-Bench | — | 53.3% |
| Mystery Game Puzzles | — | 56% |
| ForecastBench | 60.6 | — |
Math GPT-6 Sol leads
Gemini 2.5 Flash: 39.9 (#98), GPT-6 Sol: 87.2 (#7)
| Benchmark | Gemini 2.5 Flash | GPT-6 Sol |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 100% |
| LMArena Math | 1415 | 1402 |
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| ProofBench | — | 83% |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge GPT-6 Sol leads
Gemini 2.5 Flash: 36.4 (#168), GPT-6 Sol: 64.8 (#15)
| Benchmark | Gemini 2.5 Flash | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | 7.8% | 6.5% |
| LMArena Expert | 1426 | 1439 |
| GPQA Diamond | — | 94.3% |
| Humanity's Last Exam | 12.1% | — |
| SimpleQA Verified | — | 60.7% |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal GPT-6 Sol leads
Gemini 2.5 Flash: 41.8 (#32), GPT-6 Sol: 47.6 (#10)
| Benchmark | Gemini 2.5 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1253 | 1245 |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
| SpatialViz-Bench | 36.9% | — |
Multilingual Gemini 2.5 Flash leads
Gemini 2.5 Flash: 52.3 (#88), GPT-6 Sol: 50.5 (#118)
| Benchmark | Gemini 2.5 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1409 | 1385 |
| LMArena Chinese | 1450 | 1405 |
| LMArena French | 1433 | 1410 |
| LMArena German | 1418 | 1390 |
| LMArena Japanese | 1405 | 1385 |
| LMArena Korean | 1385 | 1341 |
| LMArena Russian | 1415 | 1401 |
| LMArena Spanish | 1421 | 1384 |
Instruction Following Gemini 2.5 Flash leads
Gemini 2.5 Flash: 75.7 (#54), GPT-6 Sol: 74.5 (#94)
| Benchmark | Gemini 2.5 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1405 | 1412 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), GPT-6 Sol: 43.1 (#108)
| Benchmark | Gemini 2.5 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1419 | 1411 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference GPT-6 Sol leads
Gemini 2.5 Flash: 53.8 (#157), GPT-6 Sol: 71.9 (#18)
| Benchmark | Gemini 2.5 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1417 | 1395 |
| LMArena Creative Writing | 1400 | 1378 |
| EQ-Bench Creative Writing | 1137 | 2125 |
| LMArena Multi-Turn | 1408 | 1412 |
| Short-Story Creative Writing | 76.5% | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 4.7× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash or GPT-6 Sol?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is Gemini 2.5 Flash or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 35.8 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 Flash and GPT-6 Sol share?
29 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and GPT-6 Sol has 45.