Model comparison
Gemini 1.5 Flash (May 2024) vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 33.2 on the Noometry Index.
Last verified . 22 shared benchmarks.
GoogleSummary
- They share 22 benchmarks with published results for both. Gemini 1.5 Flash (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 math, where GPT-6 Sol leads 87.2 to 22.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.3% for Gemini 1.5 Flash (May 2024) and 100% for GPT-6 Sol.
Side by side
| Gemini 1.5 Flash (May 2024) | GPT-6 Sol | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 33.2 | 61.8 |
| Released | 2024-05-14 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 42 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Gemini 1.5 Flash (May 2024): 34.4 (#236), GPT-6 Sol: 60.1 (#11)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1261 | 1447 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| LMArena WebDev | — | 1688 |
| SciCode | — | 57.6% |
| WeirdML | 24.9% | — |
| BigCodeBench Instruct | 43.5% | — |
| BigCodeBench Complete | 55.1% | — |
| ALE-Bench | — | 2,462 |
| HumanEval+ | 75.6% | — |
| MBPP+ | 67.5% | — |
Agentic & Tool Use GPT-6 Sol leads
Gemini 1.5 Flash (May 2024): 26.6 (#102), GPT-6 Sol: 37.2 (#36)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-6 Sol |
|---|---|---|
| APEX-Agents | — | 54.3% |
| BALROG | 14.6% | — |
| GDP.pdf | — | 26.4% |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
Gemini 1.5 Flash (May 2024): 21.7 (#215), GPT-6 Sol: 74.0 (#9)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1418 |
| DTBench | 53.8% | 97.3% |
| Epoch Capabilities Index | 129.36 | 162.72 |
| ARC-AGI-2 | — | 89.6% |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 30.9% |
| EBR-Bench | — | 53.3% |
| Mystery Game Puzzles | — | 56% |
| LMCA | — | 59.1% |
| ForecastBench | 53.9 | — |
| PIQA | 87.5% | — |
Math GPT-6 Sol leads
Gemini 1.5 Flash (May 2024): 22.1 (#281), GPT-6 Sol: 87.2 (#7)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-6 Sol |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.3% | 100% |
| LMArena Math | 1269 | 1402 |
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| ProofBench | — | 83% |
| Omni-MATH | 30.4% | — |
| MATH Level 5 | 61.9% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
| GSM8K | 82.4% | — |
Knowledge GPT-6 Sol leads
Gemini 1.5 Flash (May 2024): 26.2 (#260), GPT-6 Sol: 64.8 (#15)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 47.3% | 94.3% |
| LMArena Expert | 1233 | 1439 |
| SimpleQA Verified | — | 60.7% |
| MMLU-Pro | 67.8% | — |
| Vectara Hallucination Rate | — | 6.5% |
| GPQA (HELM) | 43.7% | — |
| BoolQ | 85.8% | — |
| MMLU | 77.9% | — |
Multimodal GPT-6 Sol leads
Gemini 1.5 Flash (May 2024): 36.0 (#81), GPT-6 Sol: 47.6 (#10)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1141 | 1245 |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
Multilingual GPT-6 Sol leads
Gemini 1.5 Flash (May 2024): 42.9 (#189), GPT-6 Sol: 50.5 (#118)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1278 | 1385 |
| LMArena Chinese | 1295 | 1405 |
| LMArena French | 1258 | 1410 |
| LMArena German | 1262 | 1390 |
| LMArena Japanese | 1252 | 1385 |
| LMArena Korean | 1221 | 1341 |
| LMArena Russian | 1288 | 1401 |
| LMArena Spanish | 1243 | 1384 |
Instruction Following GPT-6 Sol leads
Gemini 1.5 Flash (May 2024): 66.8 (#205), GPT-6 Sol: 74.5 (#94)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1258 | 1412 |
| IFEval | 83.1% | — |
Long Context GPT-6 Sol leads
Gemini 1.5 Flash (May 2024): 39.0 (#187), GPT-6 Sol: 43.1 (#108)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1284 | 1411 |
Writing & Preference GPT-6 Sol leads
Gemini 1.5 Flash (May 2024): 48.7 (#196), GPT-6 Sol: 71.9 (#18)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1287 | 1395 |
| LMArena Creative Writing | 1285 | 1378 |
| LMArena Multi-Turn | 1253 | 1412 |
| EQ-Bench Creative Writing | — | 2125 |
| WildBench | 79.2% | — |
Frequently asked questions
Is Gemini 1.5 Flash (May 2024) better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 33.2 on the Noometry Index.
Is Gemini 1.5 Flash (May 2024) or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 34.4 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Flash (May 2024) and GPT-6 Sol share?
22 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and GPT-6 Sol has 45.