# Qwen3.7 Max vs Qwen3.8 Max

> Side-by-side benchmark comparison for Qwen3.7 Max and Qwen3.8 Max across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/qwen3-7-max-vs-qwen3-8-max
- Last updated: September 17, 2026

- Shared sourced benchmarks: 14
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Qwen3.8 Max if you want the stronger benchmark profile. Qwen3.7 Max only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Qwen3.8 Max leads overall 71.76 to 67.03.
- The clearest category separation is in agentic, where the averages are 41.1 for Qwen3.7 Max and 67.3 for Qwen3.8 Max.
- The biggest single benchmark swing is SWE-bench (Vals) in Coding, with scores of 68.8% and 85.6%.

## Model Snapshot

| Property | Qwen3.7 Max | Qwen3.8 Max |
|----------|----------|----------|
| Creator | Alibaba | Alibaba |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 67.03 | 71.76 |
| Benchmarks Covered | 41 | 60 |
| Pricing (input/output) | Pricing unavailable / Pricing unavailable | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Qwen3.8 Max
- Qwen3.7 Max public-lane score: 41.1 (Supported · #111/153)
- Qwen3.8 Max public-lane score: 67.3 (Supported · #9/153)

| Benchmark | Qwen3.7 Max | Qwen3.8 Max | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 69.7% | Coming soon | Coming soon |
| QwenClawBench | 64.3% | Coming soon | Coming soon |
| Claw-Eval | 65.2% | Coming soon | Coming soon |
| BFCL v4 | 75.0% | Coming soon | Coming soon |
| MCP Atlas | 76.4% | Coming soon | Coming soon |
| VITA-Bench | 47.9% | Coming soon | Coming soon |
| HLE w/ tools | 53.5% | 56.2% | Qwen3.8 Max |
| Gert Labs | 64.27% | Coming soon | Coming soon |
| ResearchClawBench | 18.7% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 61.0% | 67.4% | Qwen3.8 Max |
| Terminal-Bench 2.1 | Coming soon | 86.6% | Coming soon |
| CoWorkBench | Coming soon | 74.8% | Coming soon |
| JobBench | Coming soon | 53.4% | Coming soon |
| skillsBench | Coming soon | 70.2% | Coming soon |
| Agents' Last Exam | Coming soon | 52.4% | Coming soon |
| AutomationBench | Coming soon | 27.3% | Coming soon |
| Toolathlon-Verified | Coming soon | 72.5% | Coming soon |
| WideResearch | Coming soon | 81.9% | Coming soon |
| OSWorld-Verified | Coming soon | 86.1% | Coming soon |
| OSWorld 2.0 | Coming soon | 19.4% | Coming soon |
| WebArena-Verified | Coming soon | 66.8% | Coming soon |
| AndroidWorld | Coming soon | 85.3% | Coming soon |
| MobileWorld | Coming soon | 77.8% | Coming soon |

### Coding

- Winner: Qwen3.8 Max
- Qwen3.7 Max public-lane score: 49.4 (Supported · #65/152)
- Qwen3.8 Max public-lane score: 60.8 (Supported · #20/152)

| Benchmark | Qwen3.7 Max | Qwen3.8 Max | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 80.4% | Coming soon | Coming soon |
| SWE-bench Pro | 60.6% | 67.7% | Qwen3.8 Max |
| SWE Multilingual | 78.3% | Coming soon | Coming soon |
| NL2Repo | 47.2% | 55.9% | Qwen3.8 Max |
| SciCode | 53.5% | Coming soon | Coming soon |
| LiveCodeBench | 91.6% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 69.7% | Coming soon | Coming soon |
| OpenHarmony Bench | 53.4% | 60.8% | Qwen3.8 Max |
| LiveCodeBench (Vals) | 87.1% | 87.9% | Qwen3.8 Max |
| SWE-bench (Vals) | 68.8% | 85.6% | Qwen3.8 Max |
| Terminal-Bench 2.1 | Coming soon | 86.6% | Coming soon |
| DeepSWE | Coming soon | 56.6% | Coming soon |
| FrontierSWE | Coming soon | 73.5% | Coming soon |
| MLS-Bench Lite | Coming soon | 41.0% | Coming soon |
| PaperBench | Coming soon | 93.0% | Coming soon |
| VulcanBench v3 | Coming soon | 81.2% | Coming soon |
| FrontierSWE v2 | Coming soon | 15.8% | Coming soon |

### Multimodal & Grounded

- Winner: Coming soon
- Qwen3.7 Max public-lane score: Coming soon
- Qwen3.8 Max public-lane score: 87.4 (#5/48)

| Benchmark | Qwen3.7 Max | Qwen3.8 Max | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | Coming soon | 82.3% | Coming soon |
| MathVision | Coming soon | 95.2% | Coming soon |
| MathVision w/ Python | Coming soon | 97.7% | Coming soon |
| BabyVision | Coming soon | 82.0% | Coming soon |
| BabyVision w/ Python | Coming soon | 91.3% | Coming soon |
| ZeroBench | Coming soon | 24.0% | Coming soon |
| ZeroBench w/ Python | Coming soon | 49.0% | Coming soon |
| MedXpertQA (MM) | Coming soon | 80.4% | Coming soon |
| ScreenSpot Pro | Coming soon | 84.5% | Coming soon |
| Vision2Web | Coming soon | 69.0% | Coming soon |
| CharXiv w/o tools | Coming soon | 88.4% | Coming soon |
| CharXiv | Coming soon | 93.5% | Coming soon |
| OmniDocBench 1.5 | Coming soon | 92.1% | Coming soon |
| OCRBench V2 | Coming soon | 74.2% | Coming soon |
| CC-OCR | Coming soon | 79.6% | Coming soon |
| RealWorldQA | Coming soon | 88.0% | Coming soon |
| ERQA | Coming soon | 77.8% | Coming soon |
| SimpleVQA | Coming soon | 75.0% | Coming soon |
| PerceptionBench | Coming soon | 63.5% | Coming soon |
| Video-MME (with subtitle) | Coming soon | 90.4% | Coming soon |
| VideoMMMU | Coming soon | 88.7% | Coming soon |
| MMVU | Coming soon | 82.4% | Coming soon |
| MLVU (M-Avg) | Coming soon | 90.8% | Coming soon |
| LVBench | Coming soon | 81.8% | Coming soon |

### Reasoning

- Winner: Coming soon
- Qwen3.7 Max public-lane score: 75.1 (Unranked · 3 rankable rows)
- Qwen3.8 Max public-lane score: 86.5 (Unranked · 2 rankable rows)

| Benchmark | Qwen3.7 Max | Qwen3.8 Max | Winner |
|-----------|-----------|-----------|--------|
| MRCRv2 | 90.4% | 92.9% | Qwen3.8 Max |
| CritPt | 13.4% | Coming soon | Coming soon |
| LongBench v2 | Coming soon | 66.3% | Coming soon |

### Knowledge

- Winner: Qwen3.8 Max
- Qwen3.7 Max public-lane score: 61.7 (Supported · #28/183)
- Qwen3.8 Max public-lane score: 68.8 (Supported · #17/183)

| Benchmark | Qwen3.7 Max | Qwen3.8 Max | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 92.4% | 92.6% | Qwen3.8 Max |
| GPQA-D | 92.4% | 92.6% | Qwen3.8 Max |
| HLE | 41.4% | 43.6% | Qwen3.8 Max |
| MMLU-Pro | 89.6% | Coming soon | Coming soon |
| MMLU-Redux | 95% | Coming soon | Coming soon |
| SuperGPQA | 73.6% | Coming soon | Coming soon |
| MMMLU | 90.3% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 90.2% | 93.7% | Qwen3.8 Max |
| MMLU-Pro (Vals) | 89.3% | 88.6% | Qwen3.7 Max |
| HLE w/o tools | Coming soon | 43.6% | Coming soon |

### Instruction Following

- Winner: Tie
- Qwen3.7 Max public-lane score: 91.1 (#16/123)
- Qwen3.8 Max public-lane score: 90.7 (#18/123)

| Benchmark | Qwen3.7 Max | Qwen3.8 Max | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 94.3% | Coming soon | Coming soon |
| IFBench | 79.1% | 82.8% | Qwen3.8 Max |

### Multilingual

- Winner: Coming soon
- Qwen3.7 Max public-lane score: 100 (#1/12)
- Qwen3.8 Max public-lane score: Coming soon

| Benchmark | Qwen3.7 Max | Qwen3.8 Max | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | 87% | Coming soon | Coming soon |
| NOVA-63 | 59.0% | Coming soon | Coming soon |
| INCLUDE | 86.2% | Coming soon | Coming soon |
| MAXIFE | 89.2% | Coming soon | Coming soon |
| PolyMath | 86.5% | Coming soon | Coming soon |

### Mathematics

- Winner: Coming soon
- Qwen3.7 Max public-lane score: 82.1 (Unranked · 3 rankable rows)
- Qwen3.8 Max public-lane score: Coming soon

| Benchmark | Qwen3.7 Max | Qwen3.8 Max | Winner |
|-----------|-----------|-----------|--------|
| HMMT Feb 2026 | 97.1% | Coming soon | Coming soon |
| IMOAnswerBench | 90.0% | Coming soon | Coming soon |
| Apex | 44.5% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Qwen3.7 Max or Qwen3.8 Max?

Qwen3.8 Max is ahead overall on BenchLM right now.

### Where is the biggest gap between Qwen3.7 Max and Qwen3.8 Max?

The widest category gap is in agentic, where the averages are 41.1 for Qwen3.7 Max and 67.3 for Qwen3.8 Max.

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

Qwen3.7 Max currently has 41 sourced benchmark scores on BenchLM.

### How many benchmarks does Qwen3.8 Max cover on BenchLM?

Qwen3.8 Max currently has 60 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Qwen3.7 Max vs Qwen3.8 Max Preview](/compare/qwen3-7-max-vs-qwen3-8-max-preview)
- [Qwen3.8 Max vs Qwen3.8 Max Preview](/compare/qwen3-8-max-vs-qwen3-8-max-preview)
- [Qwen3.7 Max vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-qwen3-7-max)
- [Qwen3.8 Max vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-qwen3-8-max)

## Explore More

- [Qwen3.7 Max profile](/models/qwen3-7-max)
- [Qwen3.8 Max profile](/models/qwen3-8-max)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)