Model comparison
Gemini 3.8 Flash vs GPT-6 Sol
Gemini 3.8 Flash and GPT-6 Sol score almost the same on the Noometry Index (61.8 vs 61.8), so choose on price, context window or the category you care about most.
Last verified . 43 shared benchmarks.
GoogleSummary
- They share 43 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 7 categories and GPT-6 Sol in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 65.3.
- The biggest single-benchmark swing is FrontierMath Tier 4: 22% for Gemini 3.8 Flash and 90% for GPT-6 Sol.
- Gemini 3.8 Flash is cheaper at $0.75 / $3.75 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 3.8 Flash | GPT-6 Sol | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 61.8 | 61.8 |
| Released | 2026-09-02 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.75 | $2 |
| Output $ / M tokens | $3.75 | $10 |
| Results tracked | 50 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 3.8 Flash: 59.2 (#15), GPT-6 Sol: 60.1 (#11)
| Benchmark | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| DeepSWE | 73.8% | 68.8% |
| FrontierCode | 41.2% | 49.3% |
| LMArena WebDev | 1584 | 1688 |
| SciCode | 56.6% | 57.6% |
| LMArena Coding | 1510 | 1447 |
| ALE-Bench | 1,270 | 2,462 |
| CursorBench | 39.6% | — |
| FrontierSWE | 19.6% | — |
| WeirdML | 84.8% | — |
Agentic & Tool Use Gemini 3.8 Flash leads
Gemini 3.8 Flash: 41.8 (#21), GPT-6 Sol: 37.2 (#36)
| Benchmark | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| APEX-Agents | 64.3% | 54.3% |
| GDP.pdf | 23.4% | 26.4% |
| Vending-Bench 2 | 5,094 | 14,428 |
| Remote Labor Index | 5.8% | — |
Reasoning Gemini 3.8 Flash leads
Gemini 3.8 Flash: 76.9 (#5), GPT-6 Sol: 74.0 (#9)
| Benchmark | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| ARC-AGI-2 | 89.2% | 89.6% |
| NYT Connections (extended) | 97.4% | 90.1% |
| ARC-AGI-1 | 98.5% | 95.5% |
| CritPt | 18.3% | 30.9% |
| LMArena Hard Prompts | 1508 | 1418 |
| Mystery Game Puzzles | 47% | 56% |
| DTBench | 95.7% | 97.3% |
| LMCA | 52.9% | 59.1% |
| Epoch Capabilities Index | 156.71 | 162.72 |
| Chess Puzzles | 61% | — |
| EBR-Bench | — | 53.3% |
| Surface Evolver Bench | 76.9% | — |
Math GPT-6 Sol leads
Gemini 3.8 Flash: 65.3 (#28), GPT-6 Sol: 87.2 (#7)
| Benchmark | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 68.4% | 89.8% |
| FrontierMath Tier 4 | 22% | 90% |
| OTIS Mock AIME 2024-2025 | 98.9% | 100% |
| ProofBench | 48% | 83% |
| LMArena Math | 1528 | 1402 |
Knowledge Gemini 3.8 Flash leads
Gemini 3.8 Flash: 74.8 (#2), GPT-6 Sol: 64.8 (#15)
| Benchmark | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 95.4% | 94.3% |
| SimpleQA Verified | 69.7% | 60.7% |
| LMArena Expert | 1524 | 1439 |
| Humanity's Last Exam | 44.5% | — |
| Vectara Hallucination Rate | — | 6.5% |
Multimodal GPT-6 Sol leads
Gemini 3.8 Flash: 40.7 (#45), GPT-6 Sol: 47.6 (#10)
| Benchmark | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1314 | 1245 |
| Blueprint-Bench 2 | 38.6% | 36.9% |
| Furniture Assembly | 31.7% | 58.3% |
Multilingual Gemini 3.8 Flash leads
Gemini 3.8 Flash: 58.0 (#5), GPT-6 Sol: 50.5 (#118)
| Benchmark | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1491 | 1385 |
| LMArena Chinese | 1554 | 1405 |
| LMArena French | 1498 | 1410 |
| LMArena German | 1493 | 1390 |
| LMArena Japanese | 1502 | 1385 |
| LMArena Korean | 1459 | 1341 |
| LMArena Russian | 1515 | 1401 |
| LMArena Spanish | 1485 | 1384 |
Instruction Following Gemini 3.8 Flash leads
Gemini 3.8 Flash: 78.0 (#13), GPT-6 Sol: 74.5 (#94)
| Benchmark | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1490 | 1412 |
Long Context Gemini 3.8 Flash leads
Gemini 3.8 Flash: 46.3 (#24), GPT-6 Sol: 43.1 (#108)
| Benchmark | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1508 | 1411 |
Writing & Preference Too close to call
Gemini 3.8 Flash: 72.2 (#15), GPT-6 Sol: 71.9 (#18)
| Benchmark | Gemini 3.8 Flash | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1499 | 1395 |
| LMArena Creative Writing | 1492 | 1378 |
| EQ-Bench Creative Writing | 1748 | 2125 |
| LMArena Multi-Turn | 1501 | 1412 |
Frequently asked questions
Is Gemini 3.8 Flash better than GPT-6 Sol?
Gemini 3.8 Flash and GPT-6 Sol score almost the same on the Noometry Index (61.8 vs 61.8), so choose on price, context window or the category you care about most.
Which is cheaper, Gemini 3.8 Flash or GPT-6 Sol?
Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is Gemini 3.8 Flash or GPT-6 Sol better for coding?
They score almost the same on coding (59.2 vs 60.1); test both on your own repository before choosing.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 1.05M.
How many benchmarks do Gemini 3.8 Flash and GPT-6 Sol share?
43 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and GPT-6 Sol has 45.