Gemini 3.8 Flash vs GPT-6.1 Sol
GPT-6.1 Sol leads Gemini 3.8 Flash by 13.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Gemini 3.8 Flash wins 2 and GPT-6.1 Sol wins 16 of 20 shared benchmarks. Gemini 3.8 Flash is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Gemini 3.8 Flash | GPT-6.1 Sol |
|---|---|---|
| Agentic coding | 63 | 80 |
| Long-horizon autonomy | 64 | 78 |
| Knowledge-work agents | 47 | 54 |
| Computer use | 44 | 66 |
| Security & context learning | 53 | 62 |
Shared benchmarks
| Benchmark | Gemini 3.8 Flash | GPT-6.1 Sol |
|---|---|---|
| APEX-Agentsindex | 64.3% | 60.0% |
| Vending-Bench 2index | $5,094 | $12,861 |
| ARC-AGI | 98.5% | 98.5% |
| ARC-AGI-2 | 89.2% | 94.2% |
| Chess Puzzles | 58.0% | 68.0% |
| CritPt | 18.3% | 31.7% |
| DTBench | 95.7% | 96.5% |
| FrontierCode | 41.2% | 50.2% |
| FrontierMath Tier 4 | 22.0% | 100.0% |
| FrontierMath Tiers 1-3 | 68.4% | 93.7% |
| GPQA Diamond | 95.4% | 95.4% |
| LMCA | 52.9% | 62.8% |
| MirrorCode | 38.9% | 61.1% |
| OTIS Mock AIME | 98.9% | 100.0% |
| ProofBench | 48.0% | 99.0% |
| SciCode | 56.6% | 55.8% |
| SimpleBench | 82.4% | 82.9% |
| SimpleQA Verified | 69.7% | 73.9% |
| WebDev Arena | 1568 | 1759 |
| WeirdML v3 | 7.4% | 38.3% |
Specs and price
| Gemini 3.8 Flash | GPT-6.1 Sol | |
|---|---|---|
| Agent Index | 56.2 (#21) | 70 (#5) |
| Agent $/M | $0.35 | $0.84 |
| Input / output $/M | $0.75 / $3.75 | $2.00 / $10.00 |
| Context | 1M | 1.1M |
| Released | Sep 2, 2026 | Sep 29, 2026 |
| Weights | Closed | Closed |
| API hosts | 6 | 6 |
Don’t pick one. Route.
Shogo can run Gemini 3.8 Flash and GPT-6.1 Sol side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo