Model comparison
Gemini 2.0 Flash-Lite vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 37.8 on the Noometry Index.
Last verified . 19 shared benchmarks.
GoogleSummary
- They share 19 benchmarks with published results for both. Gemini 2.0 Flash-Lite scores higher in 0 categories and GPT-6 Sol in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 34.1.
- The biggest single-benchmark swing is DTBench: 52.5% for Gemini 2.0 Flash-Lite and 97.3% for GPT-6 Sol.
Side by side
| Gemini 2.0 Flash-Lite | GPT-6 Sol | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 37.8 | 61.8 |
| Released | 2025-02-05 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 32 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Gemini 2.0 Flash-Lite: 37.9 (#185), GPT-6 Sol: 60.1 (#11)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1322 | 1447 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| LMArena WebDev | — | 1688 |
| SciCode | — | 57.6% |
| LiveBench Coding | 47.1% | — |
| ALE-Bench | — | 2,462 |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash-Lite: —, GPT-6 Sol: 37.2 (#36)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-6 Sol |
|---|---|---|
| APEX-Agents | — | 54.3% |
| GDP.pdf | — | 26.4% |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
Gemini 2.0 Flash-Lite: 22.0 (#210), GPT-6 Sol: 74.0 (#9)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 1324 | 1418 |
| DTBench | 52.5% | 97.3% |
| ARC-AGI-2 | — | 89.6% |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 30.9% |
| EBR-Bench | — | 53.3% |
| LiveBench Reasoning | 50.1% | — |
| Mystery Game Puzzles | — | 56% |
| LiveBench Data Analysis | 65.5% | — |
| LMCA | — | 59.1% |
| Epoch Capabilities Index | — | 162.72 |
| ForecastBench | 57.1 | — |
| LiveBench | 54.3% | — |
Math GPT-6 Sol leads
Gemini 2.0 Flash-Lite: 34.1 (#196), GPT-6 Sol: 87.2 (#7)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1309 | 1402 |
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 83% |
| Omni-MATH | 37.4% | — |
| LiveBench Math | 58.1% | — |
Knowledge GPT-6 Sol leads
Gemini 2.0 Flash-Lite: 35.0 (#189), GPT-6 Sol: 64.8 (#15)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-6 Sol |
|---|---|---|
| LMArena Expert | 1305 | 1439 |
| GPQA Diamond | — | 94.3% |
| SimpleQA Verified | — | 60.7% |
| MMLU-Pro | 72% | — |
| Vectara Hallucination Rate | — | 6.5% |
| GPQA (HELM) | 50% | — |
Multimodal GPT-6 Sol leads
Gemini 2.0 Flash-Lite: 31.2 (#109), GPT-6 Sol: 47.6 (#10)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1100 | 1245 |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
Multilingual GPT-6 Sol leads
Gemini 2.0 Flash-Lite: 46.0 (#161), GPT-6 Sol: 50.5 (#118)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1323 | 1385 |
| LMArena Chinese | 1339 | 1405 |
| LMArena French | 1347 | 1410 |
| LMArena German | 1306 | 1390 |
| LMArena Japanese | 1301 | 1385 |
| LMArena Korean | 1325 | 1341 |
| LMArena Russian | 1328 | 1401 |
| LMArena Spanish | 1313 | 1384 |
Instruction Following GPT-6 Sol leads
Gemini 2.0 Flash-Lite: 70.4 (#163), GPT-6 Sol: 74.5 (#94)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1305 | 1412 |
| LiveBench Instruction Following | 78.3% | — |
| IFEval | 82.4% | — |
Long Context GPT-6 Sol leads
Gemini 2.0 Flash-Lite: 40.1 (#160), GPT-6 Sol: 43.1 (#108)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1320 | 1411 |
Writing & Preference GPT-6 Sol leads
Gemini 2.0 Flash-Lite: 51.7 (#177), GPT-6 Sol: 71.9 (#18)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1330 | 1395 |
| LMArena Creative Writing | 1319 | 1378 |
| LMArena Multi-Turn | 1307 | 1412 |
| EQ-Bench Creative Writing | — | 2125 |
| WildBench | 79% | — |
| LiveBench Language | 34.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash-Lite better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 37.8 on the Noometry Index.
Is Gemini 2.0 Flash-Lite or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 37.9 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash-Lite and GPT-6 Sol share?
19 benchmarks have published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and GPT-6 Sol has 45.