Gemini 3.7 Flash vs Gemini 3.8 Flash
Gemini 3.8 Flash leads Gemini 3.7 Flash by 0.5 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Gemini 3.7 Flash wins 11 and Gemini 3.8 Flash wins 9 of 20 shared benchmarks. Gemini 3.7 Flash is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Gemini 3.7 Flash | Gemini 3.8 Flash |
|---|---|---|
| Agentic coding | 61 | 63 |
| Long-horizon autonomy | 64 | 64 |
| Knowledge-work agents | 48 | 47 |
| Computer use | 43 | 44 |
| Security & context learning | 53 | 53 |
Shared benchmarks
| Benchmark | Gemini 3.7 Flash | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agentsindex | 67.8% | 64.3% |
| DeepSWEindex | 65.5% | 73.8% |
| FrontierSWEindex | 20.3% | 19.6% |
| Remote Labor Indexindex | 5.0% | 5.8% |
| ARC-AGI | 95.5% | 98.5% |
| ARC-AGI-2 | 84.6% | 89.2% |
| Chess Puzzles | 66.0% | 58.0% |
| CritPt | 14.3% | 18.3% |
| DTBench | 96.8% | 95.7% |
| FrontierCode | 43.6% | 41.2% |
| FrontierMath Tier 4 | 36.6% | 22.0% |
| FrontierMath Tiers 1-3 | 71.6% | 68.4% |
| GPQA Diamond | 94.8% | 95.4% |
| LMCA | 50.4% | 52.9% |
| MirrorCode | 41.1% | 38.9% |
| OTIS Mock AIME | 97.2% | 98.9% |
| ProofBench | 58.0% | 48.0% |
| SciCode | 59.8% | 56.6% |
| SimpleQA Verified | 69.2% | 69.7% |
| WebDev Arena | 1587 | 1568 |
Specs and price
| Gemini 3.7 Flash | Gemini 3.8 Flash | |
|---|---|---|
| Agent Index | 55.7 (#23) | 56.2 (#21) |
| Agent $/M | $0.35 | $0.35 |
| Input / output $/M | $0.75 / $3.75 | $0.75 / $3.75 |
| Context | 1M | 1M |
| Released | Aug 13, 2026 | Sep 2, 2026 |
| Weights | Closed | Closed |
| API hosts | 6 | 6 |
Don’t pick one. Route.
Shogo can run Gemini 3.7 Flash and Gemini 3.8 Flash side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo