# Claude Sonnet 5 vs Step 3.7 Flash

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

- Canonical page: https://benchlm.ai/compare/claude-sonnet-5-vs-step-3-7-flash
- Last updated: September 18, 2026

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

## Quick Verdict

Pick Claude Sonnet 5 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

- Claude Sonnet 5 leads overall 69.68 to 49.78.
- The clearest category separation is in knowledge, where the averages are 66.5 for Claude Sonnet 5 and 48.6 for Step 3.7 Flash.
- The biggest single benchmark swing is Terminal-Bench 2.0 in Agentic, with scores of 80.4% and 59.5%.
- Step 3.7 Flash is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Claude Sonnet 5 also has the larger context window at 1M.

## Model Snapshot

| Property | Claude Sonnet 5 | Step 3.7 Flash |
|----------|----------|----------|
| Creator | Anthropic | StepFun |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 256K |
| Overall Score | 69.68 | 49.78 |
| Benchmarks Covered | 26 | 11 |
| Pricing (input/output) | $2.00 / $10.00 | $0.20 / $1.15 |

## Category Breakdown

### Agentic

- Winner: Coming soon
- Claude Sonnet 5 public-lane score: 65.9 (Supported · #11/154)
- Step 3.7 Flash public-lane score: 48.7 (Estimated · #66/154)

| Benchmark | Claude Sonnet 5 | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 3.0 | 14.6% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 80.4% | 59.5% | Claude Sonnet 5 |
| BrowseComp | 84.7% | 75.8% | Claude Sonnet 5 |
| HLE w/ tools | 57.4% | 47.2% | Claude Sonnet 5 |
| OSWorld-Verified | 81.2% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 74.5% | Coming soon | Coming soon |
| ApprenticeBench | 16% | Coming soon | Coming soon |
| DeepSearchQA | Coming soon | 92.8% | Coming soon |
| Toolathlon | Coming soon | 49.5% | Coming soon |
| Claw-Eval | Coming soon | 67.1% | Coming soon |
| Gert Labs | Coming soon | 51.57% | Coming soon |

### Coding

- Winner: Coming soon
- Claude Sonnet 5 public-lane score: 63.9 (Supported · #13/154)
- Step 3.7 Flash public-lane score: 47.4 (Estimated · #77/154)

| Benchmark | Claude Sonnet 5 | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 85.2% | Coming soon | Coming soon |
| SWE-bench Pro | 63.2% | 56.3% | Claude Sonnet 5 |
| SWE Multilingual | 78.3% | Coming soon | Coming soon |
| SWE Multimodal | 28.1% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 80.4% | 59.5% | Claude Sonnet 5 |
| FrontierCode 1.1 Main | 42.7% | Coming soon | Coming soon |
| cursorBench32 | 61.5% | Coming soon | Coming soon |
| VulcanBench CII v1 | 89.2% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 82.4% | Coming soon | Coming soon |
| SWE-bench (Vals) | 79.6% | Coming soon | Coming soon |
| cursorBench40 | 34.1% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Coming soon
- Claude Sonnet 5 public-lane score: 77.4 (#14/48)
- Step 3.7 Flash public-lane score: 71 (Unranked · 3 rankable rows)

| Benchmark | Claude Sonnet 5 | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | 88.3% | Coming soon | Coming soon |
| CharXiv w/o tools | 77% | Coming soon | Coming soon |
| SimpleVQA | Coming soon | 79.2% | Coming soon |
| V* | Coming soon | 95.3% | Coming soon |

### Reasoning

- Winner: Coming soon
- Claude Sonnet 5 public-lane score: 77.4 (Unranked · 2 rankable rows)
- Step 3.7 Flash public-lane score: 71.7 (Unranked · 2 rankable rows)

### Knowledge

- Winner: Coming soon
- Claude Sonnet 5 public-lane score: 66.5 (Supported · #20/184)
- Step 3.7 Flash public-lane score: 48.6 (Estimated · #94/184)

| Benchmark | Claude Sonnet 5 | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| HLE | 57.4% | Coming soon | Coming soon |
| HLE w/o tools | 43.2% | Coming soon | Coming soon |
| HLE-Verified | 31.0% | Coming soon | Coming soon |
| LABBench2 | 80.1% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 88.9% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 87.5% | Coming soon | Coming soon |

### Instruction Following

- Winner: Coming soon
- Claude Sonnet 5 public-lane score: Coming soon
- Step 3.7 Flash public-lane score: 80.6 (#53/124)

## FAQ

### Which is better overall, Claude Sonnet 5 or Step 3.7 Flash?

Claude Sonnet 5 is ahead overall on BenchLM right now.

### Where is the biggest gap between Claude Sonnet 5 and Step 3.7 Flash?

The widest category gap is in knowledge, where the averages are 66.5 for Claude Sonnet 5 and 48.6 for Step 3.7 Flash.

### How many benchmarks does Claude Sonnet 5 cover on BenchLM?

Claude Sonnet 5 currently has 26 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

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

## Explore More

- [Claude Sonnet 5 profile](/models/claude-sonnet-5)
- [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)