# dots3-note Preview vs Step 3.7 Flash

> Side-by-side benchmark comparison for dots3-note Preview and Step 3.7 Flash across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/dots3-note-preview-vs-step-3-7-flash
- Last updated: September 28, 2026

- Shared sourced benchmarks: 8
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick dots3-note Preview if you want the stronger benchmark profile. Step 3.7 Flash only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- dots3-note Preview leads overall 62.64 to 41.35.
- The clearest category separation is in agentic, where the averages are 56.4 for dots3-note Preview and 35.6 for Step 3.7 Flash.
- The biggest single benchmark swing is Terminal-Bench 2.1 in Agentic, with scores of 75.1% and 59.5%.
- dots3-note Preview is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- dots3-note Preview also has the larger context window at 512K.

## Model Snapshot

| Property | dots3-note Preview | Step 3.7 Flash |
|----------|----------|----------|
| Creator | Dots Studio | StepFun |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 512K | 256K |
| Overall Score | 62.64 | 41.35 |
| Benchmarks Covered | 31 | 11 |
| Pricing (input/output) | $0.00 / $0.00 | $0.20 / $1.15 |

## Category Breakdown

### Agentic

- Winner: Directional only
- dots3-note Preview public-lane score: 56.4 (Estimated · #28/117)
- Step 3.7 Flash public-lane score: 35.6 (Estimated · #64/117)

| Benchmark | dots3-note Preview | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| Claw-Eval | 73.4% | 67.1% | dots3-note Preview |
| Terminal-Bench 2.1 | 75.1% | 59.5% | dots3-note Preview |
| Toolathlon-Verified | 55.6% | Coming soon | Coming soon |
| skillsBench | 52.8% | Coming soon | Coming soon |
| APEX-Agents | 30.8% | Coming soon | Coming soon |
| BrowseComp | 83.3% | 75.8% | dots3-note Preview |
| HLE w/ tools | 52.6% | 47.2% | dots3-note Preview |
| DeepSearchQA | 92.1% | 92.8% | Step 3.7 Flash |
| WideResearch | 78.9% | Coming soon | Coming soon |
| Toolathlon | Coming soon | 49.5% | Coming soon |
| Gert Labs | Coming soon | 51.57% | Coming soon |

### Coding

- Winner: Not comparable
- dots3-note Preview public-lane score: Coming soon
- Step 3.7 Flash public-lane score: 32.2 (Estimated · #88/142)

| Benchmark | dots3-note Preview | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| Codeforces | 3056.0 | Coming soon | Coming soon |
| LiveCodeBench v6 | 91.5% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 75.1% | 59.5% | dots3-note Preview |
| SWE-bench Verified | 78.4% | Coming soon | Coming soon |
| SWE Multilingual | 75.7% | Coming soon | Coming soon |
| SWE-bench Pro | 61% | 56.3% | dots3-note Preview |
| NL2Repo | 49.8% | Coming soon | Coming soon |

### Reasoning

- Winner: Not comparable
- dots3-note Preview public-lane score: 72.9 (Unranked · 1 rankable row)
- Step 3.7 Flash public-lane score: 73 (Unranked · 2 rankable rows)

| Benchmark | dots3-note Preview | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 81.4% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- dots3-note Preview public-lane score: 67.2 (Unranked · 10 rankable rows)
- Step 3.7 Flash public-lane score: 72 (Unranked · 3 rankable rows)

| Benchmark | dots3-note Preview | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| SimpleVQA | 72.5% | 79.2% | Step 3.7 Flash |
| MMMU-Pro | 79.1% | Coming soon | Coming soon |
| MathVision | 87.7% | Coming soon | Coming soon |
| ZeroBench | 19.0% | Coming soon | Coming soon |
| CharXiv w/o tools | 83.1% | Coming soon | Coming soon |
| GDP.pdf (no tools) | 60.7% | Coming soon | Coming soon |
| PerceptionBench | 53.4% | Coming soon | Coming soon |
| BabyVision | 50.0% | Coming soon | Coming soon |
| MMVU | 79.9% | Coming soon | Coming soon |
| VideoMMMU | 86.8% | Coming soon | Coming soon |
| V* | Coming soon | 95.3% | Coming soon |

### Knowledge

- Winner: Not comparable
- dots3-note Preview public-lane score: Coming soon
- Step 3.7 Flash public-lane score: 43.2 (Estimated · #84/168)

| Benchmark | dots3-note Preview | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| HLE | 52.6% | Coming soon | Coming soon |

### Instruction Following

- Winner: Directional only
- dots3-note Preview public-lane score: 85.2 (#37/124)
- Step 3.7 Flash public-lane score: 80.6 (#53/124)

| Benchmark | dots3-note Preview | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 80.4% | Coming soon | Coming soon |
| IFEval | 93.9% | Coming soon | Coming soon |

### Mathematics

- Winner: Not comparable
- dots3-note Preview public-lane score: Coming soon
- Step 3.7 Flash public-lane score: Coming soon

| Benchmark | dots3-note Preview | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| IMOAnswerBench | 90.9% | Coming soon | Coming soon |

## FAQ

### Which is better overall, dots3-note Preview or Step 3.7 Flash?

dots3-note Preview is ahead overall on BenchLM right now.

### Where is the biggest gap between dots3-note Preview and Step 3.7 Flash?

The widest category gap is in agentic, where the averages are 56.4 for dots3-note Preview and 35.6 for Step 3.7 Flash.

### How many benchmarks does dots3-note Preview cover on BenchLM?

dots3-note Preview currently has 31 sourced benchmark scores on BenchLM.

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

Step 3.7 Flash currently has 11 sourced benchmark scores on BenchLM.

## Related Comparisons

- [dots3-note Preview vs GPT-6 Astra](/compare/dots3-note-preview-vs-gpt-6-astra)
- [Step 3.7 Flash vs GPT-6 Astra](/compare/gpt-6-astra-vs-step-3-7-flash)
- [dots3-note Preview vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-dots3-note-preview)
- [Step 3.7 Flash vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-step-3-7-flash)

## Explore More

- [dots3-note Preview profile](/models/dots3-note-preview)
- [Step 3.7 Flash profile](/models/step-3-7-flash)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)