# Gemini 3.7 Flash vs Step 5 Preview

> Side-by-side benchmark comparison for Gemini 3.7 Flash and Step 5 Preview across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gemini-3-7-flash-vs-step-5-preview
- Last updated: September 21, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Step 5 Preview if you want the stronger benchmark profile. Gemini 3.7 Flash only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Step 5 Preview leads overall 72 to 68.63.
- The clearest category separation is in multimodal & grounded, where the averages are 82.6 for Gemini 3.7 Flash and 61.2 for Step 5 Preview.
- The biggest single benchmark swing is AutomationBench in Agentic, with scores of 30.4% and 44.0%.
- Step 5 Preview is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Gemini 3.7 Flash | Step 5 Preview |
|----------|----------|----------|
| Creator | Google | StepFun |
| Type | Proprietary | Pending |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 68.63 | null |
| Benchmarks Covered | 23 | 22 |
| Pricing (input/output) | $0.75 / $3.75 | $1.00 / $2.70 |

## Category Breakdown

### Agentic

- Winner: Coming soon
- Gemini 3.7 Flash public-lane score: 59.7 (Supported · #24/154)
- Step 5 Preview public-lane score: Coming soon

| Benchmark | Gemini 3.7 Flash | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 85.8% | 85.0% | Gemini 3.7 Flash |
| Terminal-Bench 3.0 | 14.9% | Coming soon | Coming soon |
| AutomationBench | 30.4% | 44.0% | Step 5 Preview |
| OSWorld 2.0 | 47.9% | Coming soon | Coming soon |
| Agents' Last Exam | 26.3% | 29.5% | Step 5 Preview |
| Terminal-Bench 2.1 (Vals) | 77.5% | Coming soon | Coming soon |
| ApprenticeBench | 16% | Coming soon | Coming soon |
| Terminal-Bench 4.0 | Coming soon | 33.30% | Coming soon |
| CyberGym | Coming soon | 84.7% | Coming soon |
| Toolathlon-Verified | Coming soon | 74.1% | Coming soon |
| MCP Atlas | Coming soon | 85.6% | Coming soon |
| JobBench | Coming soon | 59.0% | Coming soon |
| APEX-Agents | Coming soon | 37.8% | Coming soon |
| DRACO | Coming soon | 83.3% | Coming soon |
| BrowseComp | Coming soon | 88.7% | Coming soon |

### Coding

- Winner: Coming soon
- Gemini 3.7 Flash public-lane score: 63.2 (Supported · #16/156)
- Step 5 Preview public-lane score: Coming soon

| Benchmark | Gemini 3.7 Flash | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| FrontierCode 1.1 Main | 43.6% | Coming soon | Coming soon |
| DeepSWE | 65.3% | 67.7% | Step 5 Preview |
| Terminal-Bench 2.1 | 85.8% | 85.0% | Gemini 3.7 Flash |
| FrontierSWE v2 | 20.3% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 88.7% | Coming soon | Coming soon |
| SWE-bench (Vals) | 80.8% | Coming soon | Coming soon |
| SciCode | Coming soon | 58.9% | Coming soon |
| ProgramBench | Coming soon | 80.5% | Coming soon |
| sweMarathon | Coming soon | 72.7% | Coming soon |
| MLS-Bench Lite | Coming soon | 40.5% | Coming soon |

### Reasoning

- Winner: Coming soon
- Gemini 3.7 Flash public-lane score: 77.2 (Unranked · 3 rankable rows)
- Step 5 Preview public-lane score: 78.5 (Unranked · 2 rankable rows)

| Benchmark | Gemini 3.7 Flash | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| MRCR v2 64K-128K | 97% | Coming soon | Coming soon |
| CritPt | Coming soon | 20.9% | Coming soon |

### Multimodal & Grounded

- Winner: Coming soon
- Gemini 3.7 Flash public-lane score: 82.6 (#9/49)
- Step 5 Preview public-lane score: 61.2 (#28/49)

| Benchmark | Gemini 3.7 Flash | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| CharXiv w/o tools | 84.5% | Coming soon | Coming soon |
| CharXiv | 88.7% | Coming soon | Coming soon |
| LVBench | 85.4% | Coming soon | Coming soon |
| OfficeQA Pro | Coming soon | 60.3% | Coming soon |
| MMMU-Pro | Coming soon | 76% | Coming soon |

### Knowledge

- Winner: Coming soon
- Gemini 3.7 Flash public-lane score: 69.9 (Supported · #13/186)
- Step 5 Preview public-lane score: Coming soon

| Benchmark | Gemini 3.7 Flash | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| HLE-Verified | 53.6% | Coming soon | Coming soon |
| LABBench2 | 82.1% | Coming soon | Coming soon |
| BioMysteryBench (human-solvable) | 87.1% | Coming soon | Coming soon |
| BioMysteryBench (human-difficult) | 43.5% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 93.9% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 90.1% | Coming soon | Coming soon |
| GPQA-D | Coming soon | 93.5% | Coming soon |
| HLE | Coming soon | 46.5% | Coming soon |

## FAQ

### Which is better overall, Gemini 3.7 Flash or Step 5 Preview?

Step 5 Preview is ahead overall on BenchLM right now.

### Where is the biggest gap between Gemini 3.7 Flash and Step 5 Preview?

The widest category gap is in multimodal & grounded, where the averages are 82.6 for Gemini 3.7 Flash and 61.2 for Step 5 Preview.

### How many benchmarks does Gemini 3.7 Flash cover on BenchLM?

Gemini 3.7 Flash currently has 23 sourced benchmark scores on BenchLM.

### How many benchmarks does Step 5 Preview cover on BenchLM?

Step 5 Preview currently has 22 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Gemini 3.7 Flash vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-gemini-3-7-flash)
- [Step 5 Preview vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-step-5-preview)
- [Gemini 3.7 Flash vs GPT-6 Astra](/compare/gemini-3-7-flash-vs-gpt-6-astra)
- [Step 5 Preview vs GPT-6 Astra](/compare/gpt-6-astra-vs-step-5-preview)

## Explore More

- [Gemini 3.7 Flash profile](/models/gemini-3-7-flash)
- [Step 5 Preview profile](/models/step-5-preview)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)