Model comparison
Gemini 3.1 Flash Lite vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 7.1× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
GoogleSummary
- They share 30 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 1 category and GPT-6 Sol in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 22.9.
- The biggest single-benchmark swing is NYT Connections (extended): 8.2% for Gemini 3.1 Flash Lite and 90.1% for GPT-6 Sol.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 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 3.1 Flash Lite | GPT-6 Sol | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 40.8 | 61.8 |
| Released | 2026-03-03 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.25 | $2 |
| Output $ / M tokens | $1.50 | $10 |
| Results tracked | 38 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Gemini 3.1 Flash Lite: 37.8 (#188), GPT-6 Sol: 60.1 (#11)
| Benchmark | Gemini 3.1 Flash Lite | GPT-6 Sol |
|---|---|---|
| LMArena WebDev | 1256 | 1688 |
| SciCode | 41.9% | 57.6% |
| LMArena Coding | 1400 | 1447 |
| ALE-Bench | 797.73 | 2,462 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| WeirdML | 52.2% | — |
Agentic & Tool Use GPT-6 Sol leads
Gemini 3.1 Flash Lite: 30.2 (#79), GPT-6 Sol: 37.2 (#36)
| Benchmark | Gemini 3.1 Flash Lite | GPT-6 Sol |
|---|---|---|
| APEX-Agents | — | 54.3% |
| DeepResearch Bench | 37.3% | — |
| GDP.pdf | — | 26.4% |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
Gemini 3.1 Flash Lite: 22.9 (#186), GPT-6 Sol: 74.0 (#9)
| Benchmark | Gemini 3.1 Flash Lite | GPT-6 Sol |
|---|---|---|
| NYT Connections (extended) | 8.2% | 90.1% |
| CritPt | 1.1% | 30.9% |
| LMArena Hard Prompts | 1407 | 1418 |
| DTBench | 76.8% | 97.3% |
| LMCA | 35% | 59.1% |
| Epoch Capabilities Index | 144.47 | 162.72 |
| ARC-AGI-2 | — | 89.6% |
| Kagi LLM Benchmark | 67.2% | — |
| ARC-AGI-1 | — | 95.5% |
| Chess Puzzles | 25% | — |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| EBR-Bench | — | 53.3% |
| Mystery Game Puzzles | — | 56% |
| ForecastBench | 54.4 | — |
Math GPT-6 Sol leads
Gemini 3.1 Flash Lite: 40.7 (#90), GPT-6 Sol: 87.2 (#7)
| Benchmark | Gemini 3.1 Flash Lite | GPT-6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 27.7% | 89.8% |
| OTIS Mock AIME 2024-2025 | 80% | 100% |
| LMArena Math | 1428 | 1402 |
| FrontierMath Tier 4 | — | 90% |
| ProofBench | — | 83% |
Knowledge GPT-6 Sol leads
Gemini 3.1 Flash Lite: 41.9 (#104), GPT-6 Sol: 64.8 (#15)
| Benchmark | Gemini 3.1 Flash Lite | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 81.8% | 94.3% |
| Vectara Hallucination Rate | 8.2% | 6.5% |
| LMArena Expert | 1398 | 1439 |
| Humanity's Last Exam | 8.6% | — |
| SimpleQA Verified | — | 60.7% |
Multimodal GPT-6 Sol leads
Gemini 3.1 Flash Lite: 39.4 (#60), GPT-6 Sol: 47.6 (#10)
| Benchmark | Gemini 3.1 Flash Lite | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1240 | 1245 |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
Multilingual Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 52.3 (#86), GPT-6 Sol: 50.5 (#118)
| Benchmark | Gemini 3.1 Flash Lite | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1411 | 1385 |
| LMArena Chinese | 1461 | 1405 |
| LMArena French | 1424 | 1410 |
| LMArena German | 1429 | 1390 |
| LMArena Japanese | 1413 | 1385 |
| LMArena Korean | 1392 | 1341 |
| LMArena Russian | 1420 | 1401 |
| LMArena Spanish | 1421 | 1384 |
Instruction Following GPT-6 Sol leads
Gemini 3.1 Flash Lite: 72.7 (#131), GPT-6 Sol: 74.5 (#94)
| Benchmark | Gemini 3.1 Flash Lite | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1377 | 1412 |
Long Context Too close to call
Gemini 3.1 Flash Lite: 42.5 (#122), GPT-6 Sol: 43.1 (#108)
| Benchmark | Gemini 3.1 Flash Lite | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1394 | 1411 |
Writing & Preference GPT-6 Sol leads
Gemini 3.1 Flash Lite: 60.9 (#94), GPT-6 Sol: 71.9 (#18)
| Benchmark | Gemini 3.1 Flash Lite | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1416 | 1395 |
| LMArena Creative Writing | 1401 | 1378 |
| LMArena Multi-Turn | 1417 | 1412 |
| EQ-Bench Creative Writing | — | 2125 |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 7.1× 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 3.1 Flash Lite or GPT-6 Sol?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is Gemini 3.1 Flash Lite or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 37.8 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 3.1 Flash Lite and GPT-6 Sol share?
30 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and GPT-6 Sol has 45.