Compare
Gemini 3.7 Flash vs Step 5 Preview
Gemini 3.7 Flash (Google DeepMind) and Step 5 Preview (StepFun) compared on benchmarks, pricing, context window, and use-case rankings.
- Step 5 Preview ranks higher for coding (95th vs 91th percentile).
| Attribute | Gemini 3.7 Flash | Step 5 Preview |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 157 | — |
| Coding | 91 | 95 |
| Math | 80 | — |
| Reasoning & Knowledge | 85 | 93 |
| Agentic & Tools | 98 | — |
| Specifications | ||
| Developer | Google DeepMind | StepFun |
| Family | Gemini | — |
| Released | Aug 13, 2026 | Sep 18, 2026 |
| Parameters | — | 600B |
| Availability | API access | API access |
| Context window | 1M | — |
| Price — $/M input | $0.75 | — |
| Price — $/M output | $3.75 | — |
| Inputs | text, image, video, file, audio | — |
| Outputs | text | — |
| Benchmarks | ||
| AIME 2024/2025 | 97% | — |
| APEX | 68% | — |
| ARC-AGI | 96% | — |
| ARC-AGI-2 | 85% | — |
| GPQA Diamond | 95% | — |
| Humanity's Last Exam | 39% | 47% |
| SciCode | 60% | 59% |
| SimpleQA Verified | 69% | — |
| WebDev Arena | 1587 | — |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Which is better for coding, Gemini 3.7 Flash or Step 5 Preview?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Step 5 Preview ranks higher — 95th vs 91th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.