# Qwen3.5 397B Benchmark Scores & Performance

> Qwen3.5 397B by Alibaba scores 55.34/100 overall, ranking #65 out of 954 AI models.

Canonical page: https://benchlm.ai/models/qwen3-5-397b

Last updated: October 17, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Alibaba |
| Source Type | Open Weight |
| Reasoning Type | Non-Reasoning |
| Context Window | 128K |
| Overall Score | 55.34/100 |
| Overall Rank | #65 of 954 |

## Family & Coverage

- Family: Qwen3.5 397B
- Variant: base
- Benchmarks covered: 73 of 639
- Sibling models: [Qwen3.5 397B (Reasoning)](/models/qwen3-5-397b-reasoning)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Terminal-Bench 2.0](/benchmarks/terminal-bench-2) | 52.5% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [BrowseComp](/benchmarks/browsecomp) | 69% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [OSWorld-Verified](/benchmarks/osworld-verified) | 62.2% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [Claw-Eval](/benchmarks/claw-eval) | 56.8% | [Claw-Eval leaderboard](https://claw-eval.github.io/) |
| [QwenClawBench](/benchmarks/qwenclawbench) | 51.8% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [τ³-bench results](/benchmarks/tau3-bench) | 68.4% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [VITA-Bench](/benchmarks/vitabench) | 43.7% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [DeepPlanning](/benchmarks/deepplanning) | 37.6% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [Toolathlon](/benchmarks/toolathlon) | 36.3% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [MCP Atlas](/benchmarks/mcpatlas) | 46.1% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [MCP-Tasks](/benchmarks/mcptasks) | 74.2% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [WideResearch](/benchmarks/wideresearch) | 74.0% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [τ²-bench results](/benchmarks/tau2-bench) | 83.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning) |
| [Gert Labs](/benchmarks/gertlabs) | 46.76% | [Gert Labs rankings](https://gertlabs.com/rankings) |
| [ResearchClawBench](/benchmarks/researchclawbench) | 14.2% | [ResearchClawBench leaderboard](https://internscience.github.io/ResearchClawBench-Home/) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 76.2% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [LiveCodeBench v6](/benchmarks/livecodebench-v6) | 83.6% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [SWE-bench Pro](/benchmarks/swe-bench-pro) | 50.9% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [SWE Multilingual](/benchmarks/swe-bench-multilingual) | 69.3% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [NL2Repo](/benchmarks/nl2repo) | 32.2% | [Qwen3.6-27B model card](https://huggingface.co/Qwen/Qwen3.6-27B) |
| [Terminal-Bench 2.0](/benchmarks/terminal-bench-2) | 52.5% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |

## Multimodal & Grounded Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [MMMU](/benchmarks/mmmu) | 85.0% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [MMMU-Pro](/benchmarks/mmmu-pro) | 79% | [Qwen: Qwen3.6-Plus multimodal comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [RealWorldQA](/benchmarks/realworldqa) | 83.9% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [OmniDocBench 1.5](/benchmarks/omnidocbench15) | 90.8% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [Video-MME (with subtitle)](/benchmarks/videommewithsub) | 87.5% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [Video-MME (w/o subtitle)](/benchmarks/videommenosub) | 83.7% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [MathVision](/benchmarks/mathvision) | 88.6% | [Qwen: Qwen3.6-Plus multimodal comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [We-Math](/benchmarks/wemath) | 87.9% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [DynaMath](/benchmarks/dynamath) | 86.3% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [SimpleVQA](/benchmarks/simplevqa) | 67.1% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [CharXiv](/benchmarks/charxiv) | 80.8% | [Qwen: Qwen3.6-Plus multimodal comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [MMLongBench-Doc](/benchmarks/mmlongbenchdoc) | 61.5% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [CC-OCR](/benchmarks/ccocr) | 82.0% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [AI2D_TEST](/benchmarks/ai2dtest) | 93.9% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [CountBench](/benchmarks/countbench) | 97.2% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [RefCOCO (avg)](/benchmarks/refcocoavg) | 92.3% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [ODINW13](/benchmarks/odinw13) | 47.0% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [ERQA](/benchmarks/erqa) | 67.5% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [VideoMMMU](/benchmarks/videommmu) | 84.7% | [Qwen: Qwen3.6-Plus multimodal comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [MLVU (M-Avg)](/benchmarks/mlvuavg) | 86.7% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [ScreenSpot Pro](/benchmarks/screenspot-pro) | 65.6% | [Qwen: Qwen3.6-Plus multimodal comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [V*](/benchmarks/vstar) | 95.8% | [Qwen: Qwen3.6-Plus multimodal comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [AA-MMMU-Pro](/benchmarks/mmmu-pro) | 52.7% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [LongBench v2](/benchmarks/longbench-v2) | 63.2% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [AI-Needle](/benchmarks/aineedle) | 68.7% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [AA-LCR](/benchmarks/lcr) | 64.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning) |
| [CritPt](/benchmarks/critpt) | 0.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [GPQA](/benchmarks/gpqa) | 88.4% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [SuperGPQA](/benchmarks/supergpqa) | 70.4% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [MMLU-Pro](/benchmarks/mmlu-pro) | 87.8% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [MMLU-Redux](/benchmarks/mmluredux) | 94.9% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [C-Eval](/benchmarks/ceval) | 93% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [HLE](/benchmarks/hle) | 28.7% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 21.4% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning) |
| [AA-GPQA Diamond](/benchmarks/gpqa-diamond) | 86.1% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning) |
| [AA-HLE](/benchmarks/aahle) | 19.8% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning) |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -37.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning) |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 24.5% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning) |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 82.7% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning) |

## Instruction Following Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [IFEval](/benchmarks/ifeval) | 92.6% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [IFBench](/benchmarks/ifbench) | 76.5% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [AA-IFBench](/benchmarks/ifbench) | 51.6% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning) |

## Multilingual Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [MMLU-ProX](/benchmarks/mmluprox) | 84.7% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [NOVA-63](/benchmarks/nova63) | 59.1% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [INCLUDE](/benchmarks/include) | 85.6% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [PolyMath](/benchmarks/polymath) | 73.3% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [MAXIFE](/benchmarks/maxife) | 88.2% | [Qwen3.5-397B-A17B model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |

## Mathematics Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AIME26](/benchmarks/aime2026) | 93.3% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [HMMT Feb 2025](/benchmarks/hmmtfeb2025) | 94.8% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [HMMT Nov 2025](/benchmarks/hmmtnov2025) | 92.7% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [HMMT Feb 2026](/benchmarks/hmmtfeb2026) | 87.9% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [MMAnswerBench](/benchmarks/mmanswerbench) | 80.9% | [Qwen: Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |

## Other Alibaba Models

- [Qwen3.8 Max](/models/qwen3-8-max) - Score: 69.66
- [Qwen3.8-Flash-Next](/models/qwen3-8-flash-next) - Score: 62.8
- [Qwen3.7 Max](/models/qwen3-7-max) - Score: 62.58
- [Qwen3.8-27B](/models/qwen3-8-27b) - Score: 59.61
- [Qwen 3.6 Max (preview)](/models/qwen3-6-max-preview) - Score: 55.08
- [Qwen3.6 Plus](/models/qwen3-6-plus) - Score: 53.78
- [Qwen3.7 Plus](/models/qwen3-7-plus) - Score: 53.76
- [Qwen3.5 Plus](/models/qwen3-5-plus) - Score: 48.85
- [Qwen3.6-27B](/models/qwen3-6-27b) - Score: 48.59
- [Qwen3.5-27B](/models/qwen3-5-27b) - Score: 48.41
- [Qwen3.7 Flash](/models/qwen3-7-flash) - Score: 46.93
- [Qwen3.5-35B-A3B](/models/qwen3-5-35b-a3b) - Score: 45.81
- [Qwen3.6-35B-A3B](/models/qwen3-6-35b-a3b) - Score: 43.51
- [Qwen3.5 Flash](/models/qwen3-5-flash) - Score: 42.82
- [Qwen3.5-122B-A10B](/models/qwen3-5-122b-a10b) - Score: 41.74
- [Qwen3 Max](/models/qwen3-max) - Score: 39.57
- [Qwen2.5-72B](/models/qwen2-5-72b) - Score: 28.74
- [Qwen3-Omni-30B-A3B-Instruct](/models/qwen3-omni-30b-a3b-instruct) - Score: 28.08
- [Qwen2.5 Coder 32B Instruct](/models/qwen2-5-coder-32b-instruct) - Score: 26.61
- [Qwen3 235B 2507](/models/qwen3-235b-2507) - Score: not computed
- [Qwen3.8-Omni-Flash](/models/qwen3-8-omni-flash) - Score: not computed
- [Qwen3 235B-A22B (Reasoning)](/models/qwen3-235b-a22b-reasoning) - Score: not computed
- [Qwen3 32B (Reasoning)](/models/qwen3-32b-reasoning) - Score: not computed
- [Qwen3 235B 2507 (Reasoning)](/models/qwen3-235b-2507-reasoning) - Score: not computed
- [Qwen3 235B-A22B](/models/qwen3-235b-a22b) - Score: not computed
- [Qwen3 32B](/models/qwen3-32b) - Score: not computed
- [QwQ-32B](/models/qwq-32b) - Score: not computed
- [Qwen3-Coder 480B-A35B](/models/qwen3-coder-480b-a35b) - Score: not computed
- [Qwen2.5-Max](/models/qwen2-5-max) - Score: not computed
- [Qwen2.5-VL-32B](/models/qwen2-5-vl-32b) - Score: not computed
- [Qwen3.5 397B (Reasoning)](/models/qwen3-5-397b-reasoning) - Score: not computed
- [Qwen2.5-1M](/models/qwen2-5-1m) - Score: not computed
- [Qwen3.8-27B (Chutes TEE)](/models/qwen3-8-27b-chutes) - Score: not computed
- [Qwen3-Reranker-4B](/models/qwen3-reranker-4b) - Score: not computed
- [Alibaba GTE Reranker ModernBERT-base](/models/gte-reranker-modernbert-base) - Score: not computed
- [Raw Qwen3 0.6B direct logits](/models/raw-qwen3-0-6b) - Score: not computed
- [Raw Qwen3 1.7B direct logits](/models/raw-qwen3-1-7b) - Score: not computed
- [Raw Qwen3 4B Instruct 2507 direct logits](/models/raw-qwen3-4b-instruct-2507) - Score: not computed
- [Raw Qwen3 8B direct logits](/models/raw-qwen3-8b) - Score: not computed
- [Qwen3.8 Max Preview](/models/qwen3-8-max-preview) - Score: not computed
- [Qwen3-ASR 0.6B](/models/qwen3-asr-0-6b) - Score: not computed
- [Qwen3-ASR 1.7B](/models/qwen3-asr-1-7b) - Score: not computed
- [Qwen-AgentWorld-35B-A3B](/models/qwen-agentworld-35b-a3b) - Score: not computed
- [Qwen3-Omni-30B-A3B-Thinking](/models/qwen3-omni-30b-a3b-thinking) - Score: not computed
- [Qwen2.5-Omni 7B](/models/qwen2-5-omni-7b) - Score: not computed
- [Qwen2-Audio 7B Instruct](/models/qwen2-audio-7b-instruct) - Score: not computed
- [Qwen-Audio 7B](/models/qwen-audio-7b) - Score: not computed
- [Qwen-Audio-Chat 7B](/models/qwen-audio-chat-7b) - Score: not computed
- [Qwen4 27B](/models/qwen4-27b) - Score: not computed
- [Qwen4 Flash & Plus](/models/qwen4-flash-plus) - Score: not computed
- [Qwen4 Max](/models/qwen4-max) - Score: not computed