# Step 3.7 Flash Benchmark Scores & Performance

> Step 3.7 Flash by StepFun scores 43.74/100 overall, ranking #123 out of 935 AI models.

Canonical page: https://benchlm.ai/models/step-3-7-flash

Last updated: October 14, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | StepFun |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 256K |
| Overall Score | 43.74/100 |
| Overall Rank | #123 of 935 |

## Family & Coverage

- Family: Step 3.7 Flash
- Variant: base
- Benchmarks covered: 28 of 629
- Related earlier model: [Step 3.5 Flash](/models/step-3-5-flash)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 59.5% | [StepFun: Step 3.7 Flash](https://static.stepfun.com/blog/step-3.7-flash/) |
| [BrowseComp](/benchmarks/browsecomp) | 75.8% | [StepFun: Step 3.7 Flash](https://static.stepfun.com/blog/step-3.7-flash/) |
| [DeepSearchQA](/benchmarks/deepsearchqa) | 92.8% | [StepFun: Step 3.7 Flash](https://static.stepfun.com/blog/step-3.7-flash/) |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 25.8% | [StepFun: Step 3.7 Flash](https://static.stepfun.com/blog/step-3.7-flash/) |
| [Toolathlon](/benchmarks/toolathlon) | 49.5% | [StepFun: Step 3.7 Flash](https://static.stepfun.com/blog/step-3.7-flash/) |
| [Claw-Eval](/benchmarks/claw-eval) | 67.1% | [StepFun: Step 3.7 Flash](https://static.stepfun.com/blog/step-3.7-flash/) |
| [HLE w/ tools](/benchmarks/hlewithtools) | 47.2% | [StepFun: Step 3.7 Flash](https://static.stepfun.com/blog/step-3.7-flash/) |
| [Gert Labs](/benchmarks/gertlabs) | 51.57% | [Gert Labs rankings](https://gertlabs.com/rankings) |
| [τ²-bench results](/benchmarks/tau2-bench) | 98.5% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |
| [APEX-Agents-AA](/benchmarks/apexagentsaa) | 14.8% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |
| [GDPval-AA](/benchmarks/gdpvalaa) | 954 | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [SWE-bench Pro](/benchmarks/swe-bench-pro) | 56.3% | [StepFun: Step 3.7 Flash](https://static.stepfun.com/blog/step-3.7-flash/) |
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 59.5% | [StepFun: Step 3.7 Flash](https://static.stepfun.com/blog/step-3.7-flash/) |
| [AA-SciCode](/benchmarks/aascicode) | 43.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |
| [AA Coding Index](/benchmarks/aacodingindex) | 39.6% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |

## Multimodal & Grounded Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [SimpleVQA](/benchmarks/simplevqa) | 79.2% | [StepFun: Step 3.7 Flash](https://static.stepfun.com/blog/step-3.7-flash/) |
| [V*](/benchmarks/vstar) | 95.3% | [StepFun: Step 3.7 Flash](https://static.stepfun.com/blog/step-3.7-flash/) |
| [AA-MMMU-Pro](/benchmarks/mmmu-pro) | 75.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |
| [Design Arena Website](/benchmarks/designarenawebsite) | 1198 | [OpenRouter model benchmarks](https://openrouter.ai/stepfun/step-3.7-flash/benchmarks) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AA-LCR](/benchmarks/lcr) | 73.7% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |
| [CritPt](/benchmarks/critpt) | 2.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 19.5% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |
| [AA-GPQA Diamond](/benchmarks/gpqa-diamond) | 80.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |
| [AA-HLE](/benchmarks/aahle) | 21.4% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -37.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 25.8% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 85.0% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |

## Instruction Following Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AA-IFBench](/benchmarks/ifbench) | 67.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/step-3-7-flash) |

## Other StepFun Models

- [Step 5 Preview](/models/step-5-preview) - Score: 69.43
- [Step 3.5 Flash](/models/step-3-5-flash) - Score: 42.13
- [Step-Audio](/models/step-audio) - Score: not computed
- [Step-Audio-Chat 130B](/models/step-audio-chat-130b) - Score: not computed