# Inkling-Small vs Qwen3.5 397B

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

- Canonical page: https://benchlm.ai/compare/inkling-small-vs-qwen3-5-397b
- Last updated: September 10, 2026

- Shared sourced benchmarks: 11
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Inkling-Small 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

- Inkling-Small leads overall 59.25 to 54.7.
- The clearest category separation is in instruction following, where the averages are 89.6 for Inkling-Small and 0 for Qwen3.5 397B.
- The biggest single benchmark swing is MCP Atlas in Agentic, with scores of 79.6% and 46.1%.
- Inkling-Small is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Inkling-Small also has the larger context window at 1M.

## Model Snapshot

| Property | Inkling-Small | Qwen3.5 397B |
|----------|----------|----------|
| Creator | Thinking Machines Lab | Alibaba |
| Type | Open Weight | Open Weight |
| Reasoning | Hybrid | Non-Reasoning |
| Context | 1M | 128K |
| Overall Score | 59.25 | 54.7 |
| Benchmarks Covered | 25 | 38 |
| Pricing (input/output) | $0.58 / $1.44 | $0.60 / $3.60 |

## Category Breakdown

### Agentic

- Winner: Coming soon
- Inkling-Small public-lane score: 36.9 (Supported · #128/152)
- Qwen3.5 397B public-lane score: 46.8 (Estimated · #71/152)

| Benchmark | Inkling-Small | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 64.7% | 52.5% | Inkling-Small |
| BrowseComp | 77.4% | 62% | Inkling-Small |
| MCP Atlas | 79.6% | 46.1% | Inkling-Small |
| Toolathlon-Verified | 54.4% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 55.1% | Coming soon | Coming soon |
| Claw-Eval | Coming soon | 56.8% | Coming soon |
| QwenClawBench | Coming soon | 51.8% | Coming soon |
| τ³-bench results | Coming soon | 68.4% | Coming soon |
| VITA-Bench | Coming soon | 43.7% | Coming soon |
| DeepPlanning | Coming soon | 37.6% | Coming soon |
| Toolathlon | Coming soon | 36.3% | Coming soon |
| MCP-Tasks | Coming soon | 74.2% | Coming soon |
| WideResearch | Coming soon | 74.0% | Coming soon |
| Gert Labs | Coming soon | 46.76% | Coming soon |
| ResearchClawBench | Coming soon | 14.2% | Coming soon |

### Coding

- Winner: Coming soon
- Inkling-Small public-lane score: 43.8 (Supported · #97/151)
- Qwen3.5 397B public-lane score: 50.2 (Estimated · #59/151)

| Benchmark | Inkling-Small | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 80.2% | 76.2% | Inkling-Small |
| SWE-bench Pro | 55.9% | 50.9% | Inkling-Small |
| Terminal-Bench 2.0 | 64.7% | Coming soon | Coming soon |
| SciCode | 48.7% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 85.9% | Coming soon | Coming soon |
| SWE-bench (Vals) | 82.2% | Coming soon | Coming soon |
| LiveCodeBench v6 | Coming soon | 83.6% | Coming soon |

### Multimodal & Grounded

- Winner: Qwen3.5 397B
- Inkling-Small public-lane score: 48.8 (#39/48)
- Qwen3.5 397B public-lane score: 63 (#27/48)

| Benchmark | Inkling-Small | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 74% | 79% | Qwen3.5 397B |
| CharXiv | 81.3% | 80.8% | Inkling-Small |
| CharXiv w/o tools | 77.4% | Coming soon | Coming soon |
| MathVision | Coming soon | 88.6% | Coming soon |
| VideoMMMU | Coming soon | 84.7% | Coming soon |
| ScreenSpot Pro | Coming soon | 65.6% | Coming soon |
| V* | Coming soon | 95.8% | Coming soon |

### Reasoning

- Winner: Coming soon
- Inkling-Small public-lane score: 42.7 (Unranked · 3 rankable rows)
- Qwen3.5 397B public-lane score: 59.8 (Unranked · 2 rankable rows)

| Benchmark | Inkling-Small | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 40.1% | Coming soon | Coming soon |
| CritPt | 8.3% | Coming soon | Coming soon |
| LongBench v2 | Coming soon | 63.2% | Coming soon |
| AI-Needle | Coming soon | 68.7% | Coming soon |

### Knowledge

- Winner: Coming soon
- Inkling-Small public-lane score: 56.5 (Supported · #46/183)
- Qwen3.5 397B public-lane score: 50.2 (Estimated · #77/183)

| Benchmark | Inkling-Small | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 89.5% | 88.4% | Inkling-Small |
| GPQA-D | 89.5% | Coming soon | Coming soon |
| HLE | 47.8% | 28.7% | Inkling-Small |
| HLE w/o tools | 31.6% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 83.6% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 85.6% | Coming soon | Coming soon |
| SuperGPQA | Coming soon | 70.4% | Coming soon |
| MMLU-Pro | Coming soon | 87.8% | Coming soon |
| MMLU-Redux | Coming soon | 94.9% | Coming soon |
| C-Eval | Coming soon | 93% | Coming soon |

### Instruction Following

- Winner: Coming soon
- Inkling-Small public-lane score: 89.6 (#25/123)
- Qwen3.5 397B public-lane score: 0 (#123/123)

| Benchmark | Inkling-Small | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 82.2% | Coming soon | Coming soon |
| IFEval | Coming soon | 92.6% | Coming soon |

### Multilingual

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

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

### Mathematics

- Winner: Coming soon
- Inkling-Small public-lane score: 76.9 (Unranked · 2 rankable rows)
- Qwen3.5 397B public-lane score: 74.2 (Unranked · 5 rankable rows)

| Benchmark | Inkling-Small | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 95.5% | 93.3% | Inkling-Small |
| HMMT Feb 2026 | 90.2% | 87.9% | Inkling-Small |
| HMMT Feb 2025 | Coming soon | 94.8% | Coming soon |
| HMMT Nov 2025 | Coming soon | 92.7% | Coming soon |
| MMAnswerBench | Coming soon | 80.9% | Coming soon |

## FAQ

### Which is better overall, Inkling-Small or Qwen3.5 397B?

Inkling-Small is ahead overall on BenchLM right now.

### Where is the biggest gap between Inkling-Small and Qwen3.5 397B?

The widest category gap is in instruction following, where the averages are 89.6 for Inkling-Small and 0 for Qwen3.5 397B.

### How many benchmarks does Inkling-Small cover on BenchLM?

Inkling-Small currently has 25 sourced benchmark scores on BenchLM.

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

Qwen3.5 397B currently has 38 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Inkling-Small vs Inkling](/compare/inkling-vs-inkling-small)
- [Qwen3.5 397B vs Inkling](/compare/inkling-vs-qwen3-5-397b)
- [Inkling-Small vs Qwen3.5 397B (Reasoning)](/compare/inkling-small-vs-qwen3-5-397b-reasoning)
- [Qwen3.5 397B vs Qwen3.5 397B (Reasoning)](/compare/qwen3-5-397b-vs-qwen3-5-397b-reasoning)

## Explore More

- [Inkling-Small profile](/models/inkling-small)
- [Qwen3.5 397B profile](/models/qwen3-5-397b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)