# Qwen3.5 397B vs Step 5 Preview

> Side-by-side benchmark comparison for Qwen3.5 397B and Step 5 Preview across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/qwen3-5-397b-vs-step-5-preview
- Last updated: September 21, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Step 5 Preview if you want the stronger benchmark profile. Qwen3.5 397B 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 55.25.
- The clearest category separation is in reasoning, where the averages are 59.8 for Qwen3.5 397B and 78.5 for Step 5 Preview.
- The biggest single benchmark swing is MCP Atlas in Agentic, with scores of 46.1% and 85.6%.
- Step 5 Preview is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Step 5 Preview also has the larger context window at 1M.

## Model Snapshot

| Property | Qwen3.5 397B | Step 5 Preview |
|----------|----------|----------|
| Creator | Alibaba | StepFun |
| Type | Open Weight | Pending |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 128K | 1M |
| Overall Score | 55.25 | null |
| Benchmarks Covered | 38 | 22 |
| Pricing (input/output) | $0.60 / $3.60 | $1.00 / $2.70 |

## Category Breakdown

### Agentic

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 46.9 (Estimated · #79/154)
- Step 5 Preview public-lane score: Coming soon

| Benchmark | Qwen3.5 397B | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 52.5% | Coming soon | Coming soon |
| BrowseComp | 62% | 88.7% | Step 5 Preview |
| Claw-Eval | 56.8% | Coming soon | Coming soon |
| QwenClawBench | 51.8% | Coming soon | Coming soon |
| τ³-bench results | 68.4% | Coming soon | Coming soon |
| VITA-Bench | 43.7% | Coming soon | Coming soon |
| DeepPlanning | 37.6% | Coming soon | Coming soon |
| Toolathlon | 36.3% | Coming soon | Coming soon |
| MCP Atlas | 46.1% | 85.6% | Step 5 Preview |
| MCP-Tasks | 74.2% | Coming soon | Coming soon |
| WideResearch | 74.0% | Coming soon | Coming soon |
| Gert Labs | 46.76% | Coming soon | Coming soon |
| ResearchClawBench | 14.2% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 85.0% | Coming soon |
| Terminal-Bench 4.0 | Coming soon | 33.30% | Coming soon |
| CyberGym | Coming soon | 84.7% | Coming soon |
| AutomationBench | Coming soon | 44.0% | Coming soon |
| Toolathlon-Verified | Coming soon | 74.1% | Coming soon |
| JobBench | Coming soon | 59.0% | Coming soon |
| APEX-Agents | Coming soon | 37.8% | Coming soon |
| DRACO | Coming soon | 83.3% | Coming soon |
| Agents' Last Exam | Coming soon | 29.5% | Coming soon |

### Coding

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 50.8 (Estimated · #60/156)
- Step 5 Preview public-lane score: Coming soon

| Benchmark | Qwen3.5 397B | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 76.2% | Coming soon | Coming soon |
| LiveCodeBench v6 | 83.6% | Coming soon | Coming soon |
| SWE-bench Pro | 50.9% | Coming soon | Coming soon |
| DeepSWE | Coming soon | 67.7% | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 85.0% | 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
- Qwen3.5 397B public-lane score: 59.8 (Unranked · 2 rankable rows)
- Step 5 Preview public-lane score: 78.5 (Unranked · 2 rankable rows)

| Benchmark | Qwen3.5 397B | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 63.2% | Coming soon | Coming soon |
| AI-Needle | 68.7% | Coming soon | Coming soon |
| CritPt | Coming soon | 20.9% | Coming soon |

### Multimodal & Grounded

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 62.9 (#27/49)
- Step 5 Preview public-lane score: 61.2 (#28/49)

| Benchmark | Qwen3.5 397B | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 79% | 76% | Qwen3.5 397B |
| MathVision | 88.6% | Coming soon | Coming soon |
| CharXiv | 80.8% | Coming soon | Coming soon |
| VideoMMMU | 84.7% | Coming soon | Coming soon |
| ScreenSpot Pro | 65.6% | Coming soon | Coming soon |
| V* | 95.8% | Coming soon | Coming soon |
| OfficeQA Pro | Coming soon | 60.3% | Coming soon |

### Knowledge

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 50.4 (Estimated · #83/186)
- Step 5 Preview public-lane score: Coming soon

| Benchmark | Qwen3.5 397B | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 88.4% | Coming soon | Coming soon |
| SuperGPQA | 70.4% | Coming soon | Coming soon |
| MMLU-Pro | 87.8% | Coming soon | Coming soon |
| MMLU-Redux | 94.9% | Coming soon | Coming soon |
| C-Eval | 93% | Coming soon | Coming soon |
| HLE | 28.7% | 46.5% | Step 5 Preview |
| GPQA-D | Coming soon | 93.5% | Coming soon |

### Multilingual

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 69.7 (#5/12)
- Step 5 Preview public-lane score: Coming soon

| Benchmark | Qwen3.5 397B | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | 84.7% | Coming soon | Coming soon |
| NOVA-63 | 59.1% | Coming soon | Coming soon |

### Instruction Following

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 0 (#124/124)
- Step 5 Preview public-lane score: Coming soon

| Benchmark | Qwen3.5 397B | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 92.6% | Coming soon | Coming soon |

### Mathematics

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 73.5 (Unranked · 5 rankable rows)
- Step 5 Preview public-lane score: Coming soon

| Benchmark | Qwen3.5 397B | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 93.3% | Coming soon | Coming soon |
| HMMT Feb 2025 | 94.8% | Coming soon | Coming soon |
| HMMT Nov 2025 | 92.7% | Coming soon | Coming soon |
| HMMT Feb 2026 | 87.9% | Coming soon | Coming soon |
| MMAnswerBench | 80.9% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Qwen3.5 397B or Step 5 Preview?

Step 5 Preview is ahead overall on BenchLM right now.

### Where is the biggest gap between Qwen3.5 397B and Step 5 Preview?

The widest category gap is in reasoning, where the averages are 59.8 for Qwen3.5 397B and 78.5 for Step 5 Preview.

### How many benchmarks does Qwen3.5 397B cover on BenchLM?

Qwen3.5 397B currently has 38 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

- [Qwen3.5 397B vs Qwen3.5 397B (Reasoning)](/compare/qwen3-5-397b-vs-qwen3-5-397b-reasoning)
- [Step 5 Preview vs Qwen3.5 397B (Reasoning)](/compare/qwen3-5-397b-reasoning-vs-step-5-preview)
- [Qwen3.5 397B vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-qwen3-5-397b)
- [Step 5 Preview vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-step-5-preview)

## Explore More

- [Qwen3.5 397B profile](/models/qwen3-5-397b)
- [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)