# Qwen3.6 Plus vs Qwen3.7 Plus

> Side-by-side benchmark comparison for Qwen3.6 Plus and Qwen3.7 Plus across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/qwen3-6-plus-vs-qwen3-7-plus
- Last updated: September 4, 2026

- Shared sourced benchmarks: 25
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Qwen3.7 Plus if you want the stronger benchmark profile. Qwen3.6 Plus only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Qwen3.7 Plus leads overall 62.29 to 61.49.
- The clearest category separation is in mathematics, where the averages are 62.4 for Qwen3.6 Plus and 78.3 for Qwen3.7 Plus.
- The biggest single benchmark swing is MCP Atlas in Agentic, with scores of 48.2% and 73.2%.

## Model Snapshot

| Property | Qwen3.6 Plus | Qwen3.7 Plus |
|----------|----------|----------|
| Creator | Alibaba | Alibaba |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 61.49 | 62.29 |
| Benchmarks Covered | 48 | 52 |
| Pricing (input/output) | Pricing unavailable / Pricing unavailable | N/A |

## Category Breakdown

### Agentic

- Winner: Qwen3.7 Plus
- Qwen3.6 Plus public-lane score: 36.4 (Supported · #128/151)
- Qwen3.7 Plus public-lane score: 37.7 (Supported · #126/151)

| Benchmark | Qwen3.6 Plus | Qwen3.7 Plus | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 61.6% | 70.3% | Qwen3.7 Plus |
| Claw-Eval | 58.8% | 62.7% | Qwen3.7 Plus |
| QwenClawBench | 57.2% | 61.8% | Qwen3.7 Plus |
| τ³-bench results | 70.7% | Coming soon | Coming soon |
| VITA-Bench | 44.3% | 45.6% | Qwen3.7 Plus |
| DeepPlanning | 41.5% | 62.3% | Qwen3.7 Plus |
| Toolathlon | 39.8% | Coming soon | Coming soon |
| MCP Atlas | 48.2% | 73.2% | Qwen3.7 Plus |
| MCP-Tasks | 74.1% | Coming soon | Coming soon |
| WideResearch | 74.3% | Coming soon | Coming soon |
| Gert Labs | 50.60% | Coming soon | Coming soon |
| ResearchClawBench | 18.0% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 53.2% | 52.8% | Qwen3.6 Plus |
| BFCL v4 | Coming soon | 72.9% | Coming soon |
| OSWorld-Verified | Coming soon | 73.3% | Coming soon |
| AndroidWorld | Coming soon | 81.0% | Coming soon |
| OSWorld 2.0 | Coming soon | 2.8% | Coming soon |

### Coding

- Winner: Coming soon
- Qwen3.6 Plus public-lane score: 47 (Supported · #92/183)
- Qwen3.7 Plus public-lane score: 53.1 (Estimated · #51/183)

| Benchmark | Qwen3.6 Plus | Qwen3.7 Plus | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 78.8% | 77.7% | Qwen3.6 Plus |
| SWE-bench Pro | 56.6% | 57.6% | Qwen3.7 Plus |
| SWE Multilingual | 73.8% | 75.8% | Qwen3.7 Plus |
| LiveCodeBench v6 | 87.1% | Coming soon | Coming soon |
| Vibe Code Bench | 25.56% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 86.0% | Coming soon | Coming soon |
| SWE-bench (Vals) | 73.4% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 70.3% | Coming soon |
| NL2Repo | Coming soon | 41.1% | Coming soon |
| SciCode | Coming soon | 51.3% | Coming soon |
| LiveCodeBench | Coming soon | 89.6% | Coming soon |

### Multimodal & Grounded

- Winner: Qwen3.7 Plus
- Qwen3.6 Plus public-lane score: 66.3 (#22/48)
- Qwen3.7 Plus public-lane score: 72.5 (#18/48)

| Benchmark | Qwen3.6 Plus | Qwen3.7 Plus | Winner |
|-----------|-----------|-----------|--------|
| MMMU | 86.0% | Coming soon | Coming soon |
| MMMU-Pro | 78.8% | 79% | Qwen3.7 Plus |
| MathVision | 88.0% | 90.3% | Qwen3.7 Plus |
| VideoMMMU | 84.0% | 85.4% | Qwen3.7 Plus |
| ScreenSpot Pro | 68.2% | 79.0% | Qwen3.7 Plus |
| CharXiv | 81.5% | 85.9% | Qwen3.7 Plus |
| V* | 96.9% | Coming soon | Coming soon |
| ERQA | Coming soon | 69.8% | Coming soon |
| MedXpertQA (MM) | Coming soon | 71.0% | Coming soon |
| SimpleVQA | Coming soon | 81.7% | Coming soon |
| MMSearch-Plus | Coming soon | 41.4% | Coming soon |
| RealWorldQA | Coming soon | 86.9% | Coming soon |
| OmniDocBench 1.5 | Coming soon | 91.4% | Coming soon |
| OCRBench V2 | Coming soon | 70.7% | Coming soon |
| ODINW13 | Coming soon | 51.1% | Coming soon |
| Video-MME (with subtitle) | Coming soon | 88.0% | Coming soon |
| MLVU (M-Avg) | Coming soon | 87.4% | Coming soon |

### Reasoning

- Winner: Coming soon
- Qwen3.6 Plus public-lane score: 59.3 (Unranked · 4 rankable rows)
- Qwen3.7 Plus public-lane score: 73.7 (Unranked · 3 rankable rows)

| Benchmark | Qwen3.6 Plus | Qwen3.7 Plus | Winner |
|-----------|-----------|-----------|--------|
| AI-Needle | 68.3% | Coming soon | Coming soon |
| LongBench v2 | 62% | Coming soon | Coming soon |
| CritPt | Coming soon | 9.1% | Coming soon |
| MRCRv2 | Coming soon | 91.7% | Coming soon |

### Knowledge

- Winner: Coming soon
- Qwen3.6 Plus public-lane score: 54.7 (Supported · #63/181)
- Qwen3.7 Plus public-lane score: 56.8 (Estimated · #50/181)

| Benchmark | Qwen3.6 Plus | Qwen3.7 Plus | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 90.4% | 90.3% | Qwen3.6 Plus |
| SuperGPQA | 71.6% | 71.4% | Qwen3.6 Plus |
| MMLU-Pro | 88.5% | 88.5% | Tie |
| MMLU-Redux | 94.5% | 94.5% | Tie |
| C-Eval | 93.3% | Coming soon | Coming soon |
| HLE | 28.8% | 34.7% | Qwen3.7 Plus |
| GPQA Diamond (Vals) | 87.4% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 87.7% | Coming soon | Coming soon |
| GPQA-D | Coming soon | 90.3% | Coming soon |
| MMMLU | Coming soon | 89.0% | Coming soon |

### Instruction Following

- Winner: Qwen3.7 Plus
- Qwen3.6 Plus public-lane score: 85.5 (#41/120)
- Qwen3.7 Plus public-lane score: 91.1 (#17/120)

| Benchmark | Qwen3.6 Plus | Qwen3.7 Plus | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 94.3% | 94.6% | Qwen3.7 Plus |
| IFBench | 75.8% | 79.1% | Qwen3.7 Plus |

### Multilingual

- Winner: Qwen3.7 Plus
- Qwen3.6 Plus public-lane score: 69.7 (#4/12)
- Qwen3.7 Plus public-lane score: 78.9 (#3/12)

| Benchmark | Qwen3.6 Plus | Qwen3.7 Plus | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | 84.7% | 85.4% | Qwen3.7 Plus |
| NOVA-63 | 57.9% | 58.8% | Qwen3.7 Plus |
| INCLUDE | Coming soon | 83.0% | Coming soon |
| MAXIFE | Coming soon | 88.8% | Coming soon |
| PolyMath | Coming soon | 84.0% | Coming soon |

### Mathematics

- Winner: Coming soon
- Qwen3.6 Plus public-lane score: 62.4 (#4/7)
- Qwen3.7 Plus public-lane score: 78.3 (Unranked · 3 rankable rows)

| Benchmark | Qwen3.6 Plus | Qwen3.7 Plus | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 95.3% | Coming soon | Coming soon |
| HMMT Feb 2025 | 96.7% | Coming soon | Coming soon |
| HMMT Nov 2025 | 94.6% | Coming soon | Coming soon |
| HMMT Feb 2026 | 87.8% | 92.9% | Qwen3.7 Plus |
| MMAnswerBench | 83.8% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 26.207% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 8.333% | Coming soon | Coming soon |
| IMOAnswerBench | Coming soon | 86.0% | Coming soon |
| Apex | Coming soon | 22.7% | Coming soon |

## FAQ

### Which is better overall, Qwen3.6 Plus or Qwen3.7 Plus?

Qwen3.7 Plus is ahead overall on BenchLM right now.

### Where is the biggest gap between Qwen3.6 Plus and Qwen3.7 Plus?

The widest category gap is in mathematics, where the averages are 62.4 for Qwen3.6 Plus and 78.3 for Qwen3.7 Plus.

### How many benchmarks does Qwen3.6 Plus cover on BenchLM?

Qwen3.6 Plus currently has 48 sourced benchmark scores on BenchLM.

### How many benchmarks does Qwen3.7 Plus cover on BenchLM?

Qwen3.7 Plus currently has 52 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Qwen3.6 Plus vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-qwen3-6-plus)
- [Qwen3.7 Plus vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-qwen3-7-plus)
- [Qwen3.6 Plus vs GPT-6 Astra](/compare/gpt-6-astra-vs-qwen3-6-plus)
- [Qwen3.7 Plus vs GPT-6 Astra](/compare/gpt-6-astra-vs-qwen3-7-plus)

## Explore More

- [Qwen3.6 Plus profile](/models/qwen3-6-plus)
- [Qwen3.7 Plus profile](/models/qwen3-7-plus)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)