Model profile
Qwen3.7 Max
Evidence coverage
58 of 323 tracked benchmarks are published. 36 are verified and 22 provisional. 8 of 8 categories are measured.
- Published / tracked
- 58 / 323
- Verified
- 36
- Provisional
- 22
- Categories with evidence
- 8 / 8
Evidence by category
- Agentic21 benchmarksMixed evidence
- Coding9 benchmarksMixed evidence
- Reasoning3 benchmarksMixed evidence
- Knowledge13 benchmarksMixed evidence
- Math3 benchmarksVerified
- Multilingual5 benchmarksVerified
- Multimodal1 benchmarkReported
- Inst. Following3 benchmarksMixed evidence
Qwen3.7 Max ranks #10 out of 200 models on the public leaderboard with an overall score of 72.84/100. It also ranks #9 out of 99 on the verified leaderboard. This places it in the upper tier of AI models, with competitive scores across most benchmark categories.
Qwen3.7 Max is a proprietary model with a 1M token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.
This profile currently has 58 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.
Its strongest category is Multilingual (#1), while its weakest is Agentic (#96). This performance profile makes it a well-rounded choice across a range of tasks.
Peer position
Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.
Range 70.19–74.24
- GPT-5.4OpenAICompare#874.24GPT-5.4 is #8 with a score of 74.24.
- GPT-5.5OpenAICompare#973.51GPT-5.5 is #9 with a score of 73.51.
- Qwen3.7 MaxCurrent modelAlibaba#1072.84Qwen3.7 Max is #10 with a score of 72.84.
- GPT-5.6 TerraOpenAICompare#1172.57GPT-5.6 Terra is #11 with a score of 72.57.
- Claude Opus 4.7AnthropicCompare#1271.94Claude Opus 4.7 is #12 with a score of 71.94.
- Muse SparkMetaCompare#1371.04Muse Spark is #13 with a score of 71.04.
- MiMo-V2.5-ProXiaomiCompare#1470.19MiMo-V2.5-Pro is #14 with a score of 70.19.
Category percentile
More
Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.
- Multilingual100%Eligible cohort rank #1 of 13Category score 100.0
- Inst. Following80%Eligible cohort rank #7 of 31Category score 91.0
- Knowledge63%Eligible cohort rank #20 of 52Category score 73.8
- Coding72%Eligible cohort rank #35 of 122Category score 55.0
- Agentic19%Eligible cohort rank #96 of 119Category score 38.6
Category evidence
Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #96 of 119Percentile 19thWeight 22%21 benchmarksMixed sources | 38.6 | #96 of 119 | 19th | 22% | 21 benchmarks | Mixed sources |
| CodingRank #35 of 122Percentile 72ndWeight 20%9 benchmarksMixed sources | 55.0 | #35 of 122 | 72nd | 20% | 9 benchmarks | Mixed sources |
| ReasoningRank Not rankedWeight 17%3 benchmarksMixed sources | 85.4 | Not ranked | Not available | 17% | 3 benchmarks | Mixed sources |
| KnowledgeRank #20 of 52Percentile 63rdWeight 12%13 benchmarksMixed sources | 73.8 | #20 of 52 | 63rd | 12% | 13 benchmarks | Mixed sources |
| MathRank Not rankedWeight 5%3 benchmarksVerified | 82.0 | Not ranked | Not available | 5% | 3 benchmarks | Verified |
| MultilingualRank #1 of 13Percentile 100thWeight 7%5 benchmarksVerified | 100.0 | #1 of 13 | 100th | 7% | 5 benchmarks | Verified |
| MultimodalWeight 12%1 benchmarkReported | Score pending | Not ranked | Not available | 12% | 1 benchmark | Reported |
| Inst. FollowingRank #7 of 31Percentile 80thWeight 5%3 benchmarksMixed sources | 91.0 | #7 of 31 | 80th | 5% | 3 benchmarks | Mixed sources |
Chatbot Arena performance
Scroll horizontally to inspect confidence intervals and vote counts.
| View | Elo | Confidence interval | Votes |
|---|---|---|---|
| Text Overall | 1475 | ±10.0 | 3,715 |
| Coding | 1526 | ±18.5 | 1,123 |
| Math | 1491 | ±40.1 | 219 |
| Instruction Following | 1468 | ±17.2 | 1,281 |
| Creative Writing | 1446 | ±28.0 | 481 |
| Multi-turn | 1483 | ±23.6 | 659 |
| Hard Prompts | 1496 | ±12.3 | 2,526 |
| Hard Prompts (English) | 1491 | ±17.1 | 1,296 |
| Longer Query | 1498 | ±15.8 | 1,597 |
Benchmark Details
Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.
Agentic21 benchmarks
Berkeley Function Calling Leaderboard v4
Humanity's Last Exam with tools
Artificial Analysis Agentic Index
τ²-Bench Tool-Agent-User Evaluation
GDPval-AA normalized
Gert Labs Composite Game Benchmark
Artificial Analysis Briefcase
Artificial Analysis AutomationBench
Artificial Analysis EnterpriseOps-Gym
Artificial Analysis ITBench-AA
Artificial Analysis Harvey LAB-AA
Coding9 benchmarks
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
Software Engineering Benchmark Verified
Scientific Code Benchmark
Artificial Analysis Coding Index
Artificial Analysis SciCode
Reasoning3 benchmarks
Critical Physics Tasks
Artificial Analysis Long Context Reasoning
Knowledge13 benchmarks
Humanity's Last Exam
Massive Multitask Language Understanding Professional
Graduate-Level Google-Proof Q&A
SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines
GPQA Diamond
Artificial Analysis GPQA Diamond
Artificial Analysis Humanity's Last Exam
Artificial Analysis Omniscience Index
Artificial Analysis Omniscience Accuracy
Artificial Analysis Omniscience Hallucination Rate
Math3 benchmarks
Harvard-MIT Mathematics Tournament February 2026
Multilingual5 benchmarks
Multimodal1 benchmark
Design Arena Website Elo
Inst. Following3 benchmarks
Instruction Following Benchmark
Instruction-Following Eval
Artificial Analysis IFBench
Frequently Asked Questions
How does Qwen3.7 Max perform overall in AI benchmarks?
Qwen3.7 Max currently ranks #10 out of 200 models on BenchLM's provisional leaderboard with an overall score of 72.84. It also ranks #9 out of 99 on the verified leaderboard. It is created by Alibaba. Its published context window is 1M.
Is Qwen3.7 Max good for knowledge and understanding?
Qwen3.7 Max ranks #20 out of 52 models in knowledge and understanding benchmarks with an average score of 73.8. There are stronger options in this category.
Is Qwen3.7 Max good for coding and programming?
Qwen3.7 Max ranks #35 out of 122 models in coding and programming benchmarks with an average score of 55. There are stronger options in this category.
Is Qwen3.7 Max good for mathematics?
Qwen3.7 Max has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.
Is Qwen3.7 Max good for reasoning and logic?
Qwen3.7 Max has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.
Is Qwen3.7 Max good for agentic tool use and computer tasks?
Qwen3.7 Max ranks #96 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 38.6. There are stronger options in this category.
Is Qwen3.7 Max good for multimodal and grounded tasks?
Qwen3.7 Max has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.
Is Qwen3.7 Max good for instruction following?
Qwen3.7 Max ranks #7 out of 31 models in instruction following benchmarks with an average score of 91. It is among the top performers in this category.
Is Qwen3.7 Max good for multilingual tasks?
Qwen3.7 Max ranks #1 out of 13 models in multilingual tasks benchmarks with an average score of 100. It is among the top performers in this category.
Does Qwen3.7 Max have full benchmark coverage on BenchLM?
Not yet. Qwen3.7 Max currently has 58 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.
What is the context window size of Qwen3.7 Max?
Qwen3.7 Max has a published context window of 1M, which determines how much text it can process in a single interaction.
Related Resources
Choose with this week’s evidence
Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.
Free. One email per week.