Model comparison
Gemini 3.5 Flash Lite vs GPT-6.1 Sol
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 41.5 on the Noometry Index. Gemini 3.5 Flash Lite costs 4.7× less per token, which makes it the better buy when GPT-6.1 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 3.5 Flash Lite scores higher in 1 category and GPT-6.1 Sol in 9 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 25.9.
- The biggest single-benchmark swing is FrontierMath Tier 4: 0% for Gemini 3.5 Flash Lite and 100% for GPT-6.1 Sol.
- Gemini 3.5 Flash Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 1.05M.
Side by side
| Gemini 3.5 Flash Lite | GPT-6.1 Sol | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 41.5 | 65.6 |
| Released | 2026-07-21 | 2026-09-29 |
| 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 | 39 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
Gemini 3.5 Flash Lite: 42.4 (#104), GPT-6.1 Sol: 63.2 (#8)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6.1 Sol |
|---|---|---|
| LMArena WebDev | 1440 | 1755 |
| SciCode | 41.3% | 55.8% |
| LMArena Coding | 1453 | 1487 |
| DeepSWE | — | 75.2% |
| FrontierCode | — | 50.2% |
| WeirdML | 39% | — |
| ALE-Bench | 765.27 | — |
Agentic & Tool Use GPT-6.1 Sol leads
Gemini 3.5 Flash Lite: 25.7 (#107), GPT-6.1 Sol: 39.6 (#26)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6.1 Sol |
|---|---|---|
| APEX-Agents | 29.3% | 60% |
| GDP.pdf | 10% | 32% |
Reasoning GPT-6.1 Sol leads
Gemini 3.5 Flash Lite: 27.8 (#114), GPT-6.1 Sol: 81.9 (#2)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6.1 Sol |
|---|---|---|
| ARC-AGI-2 | 10.3% | 94.2% |
| NYT Connections (extended) | 60.4% | 95.5% |
| ARC-AGI-1 | 53.5% | 98.5% |
| CritPt | 0% | 31.7% |
| Chess Puzzles | 22% | 61% |
| LMArena Hard Prompts | 1441 | 1466 |
| Mystery Game Puzzles | 19% | 80% |
| Epoch Capabilities Index | 145.13 | 166.09 |
| EBR-Bench | — | 54.3% |
| DTBench | 83.5% | — |
| LMCA | 37.6% | — |
Math GPT-6.1 Sol leads
Gemini 3.5 Flash Lite: 25.9 (#264), GPT-6.1 Sol: 93.7 (#1)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6.1 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 26% | 93.7% |
| FrontierMath Tier 4 | 0% | 100% |
| OTIS Mock AIME 2024-2025 | 71.1% | 100% |
| ProofBench | 13% | 99% |
| LMArena Math | 1433 | 1464 |
Knowledge GPT-6.1 Sol leads
Gemini 3.5 Flash Lite: 50.1 (#72), GPT-6.1 Sol: 71.8 (#4)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6.1 Sol |
|---|---|---|
| GPQA Diamond | 83.3% | 95.4% |
| LMArena Expert | 1435 | 1502 |
| SimpleQA Verified | — | 73.9% |
Multimodal GPT-6.1 Sol leads
Gemini 3.5 Flash Lite: 41.1 (#40), GPT-6.1 Sol: 52.7 (#5)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6.1 Sol |
|---|---|---|
| LMArena Vision | 1268 | 1288 |
| Furniture Assembly | — | 80% |
Multilingual Too close to call
Gemini 3.5 Flash Lite: 53.5 (#63), GPT-6.1 Sol: 54.3 (#46)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6.1 Sol |
|---|---|---|
| LMArena Non-English | 1427 | 1438 |
| LMArena Chinese | 1469 | 1477 |
| LMArena Russian | 1443 | 1455 |
| LMArena French | 1451 | — |
| LMArena German | 1454 | — |
| LMArena Japanese | 1427 | — |
| LMArena Korean | 1407 | — |
| LMArena Spanish | 1442 | — |
Instruction Following GPT-6.1 Sol leads
Gemini 3.5 Flash Lite: 74.8 (#85), GPT-6.1 Sol: 77.0 (#29)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6.1 Sol |
|---|---|---|
| LMArena Instruction Following | 1420 | 1468 |
Long Context Too close to call
Gemini 3.5 Flash Lite: 43.9 (#84), GPT-6.1 Sol: 44.9 (#54)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6.1 Sol |
|---|---|---|
| LMArena Longer Query | 1435 | 1465 |
Writing & Preference Too close to call
Gemini 3.5 Flash Lite: 64.2 (#57), GPT-6.1 Sol: 63.6 (#63)
| Benchmark | Gemini 3.5 Flash Lite | GPT-6.1 Sol |
|---|---|---|
| LMArena Text | 1435 | 1447 |
| LMArena Creative Writing | 1420 | 1432 |
| LMArena Multi-Turn | 1445 | 1449 |
| EQ-Bench Creative Writing | 1559 | — |
Frequently asked questions
Is Gemini 3.5 Flash Lite better than GPT-6.1 Sol?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 41.5 on the Noometry Index. Gemini 3.5 Flash Lite costs 4.7× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.5 Flash Lite or GPT-6.1 Sol?
Gemini 3.5 Flash Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; GPT-6.1 Sol lists at $2 and $10.
Is Gemini 3.5 Flash Lite or GPT-6.1 Sol better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 1.05M.
How many benchmarks do Gemini 3.5 Flash Lite and GPT-6.1 Sol share?
29 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and GPT-6.1 Sol has 34.