Claude Sonnet 5 vs Gemini 3.7 Flash
Gemini 3.7 Flash leads Claude Sonnet 5 by 3.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Sonnet 5 wins 3 and Gemini 3.7 Flash wins 13 of 16 shared benchmarks. Gemini 3.7 Flash is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Sonnet 5 | Gemini 3.7 Flash |
|---|---|---|
| Agentic coding | 57 | 61 |
| Long-horizon autonomy | 65 | 64 |
| Knowledge-work agents | 43 | 48 |
| Computer use | 40 | 43 |
| Security & context learning | 51 | 53 |
Shared benchmarks
| Benchmark | Claude Sonnet 5 | Gemini 3.7 Flash |
|---|---|---|
| APEX-Agentsindex | 54.5% | 67.8% |
| DeepSWEindex | 53.8% | 65.5% |
| Chess Puzzles | 45.0% | 66.0% |
| CritPt | 16.9% | 14.3% |
| DTBench | 92.5% | 96.8% |
| FrontierCode | 42.7% | 43.6% |
| FrontierMath Tier 4 | 29.3% | 36.6% |
| FrontierMath Tiers 1-3 | 65.6% | 71.6% |
| GPQA Diamond | 90.5% | 94.8% |
| LMCA | 50.0% | 50.4% |
| MirrorCode | 63.3% | 41.1% |
| OTIS Mock AIME | 94.7% | 97.2% |
| ProofBench | 77.0% | 58.0% |
| SciCode | 54.3% | 59.8% |
| SimpleQA Verified | 33.7% | 69.2% |
| WebDev Arena | 1537 | 1587 |
Specs and price
| Claude Sonnet 5 | Gemini 3.7 Flash | |
|---|---|---|
| Agent Index | 52.4 (#32) | 55.7 (#23) |
| Agent $/M | $0.92 | $0.35 |
| Input / output $/M | $2.00 / $10.00 | $0.75 / $3.75 |
| Context | 1M | 1M |
| Released | Jun 30, 2026 | Aug 13, 2026 |
| Weights | Closed | Closed |
| API hosts | 5 | 6 |
Don’t pick one. Route.
Shogo can run Claude Sonnet 5 and Gemini 3.7 Flash side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo