Qwen3.7 Plus

Qwen3.7 Plus is a reasoning model from Alibaba. 49 benchmarks count toward its score, in 7 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.58.2 ±2.8
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.13/s
Input / 1MUS dollars per 1M input tokens.$0.32
Output / 1MUS dollars per 1M output tokens.$1.28
ContextMaximum tokens in one request.1M
EloLMArena rating and rank.1454 (#39)

50 is the middle of the board. The range shows the doubt in the index.

39,334 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category. 50 is the middle.

50 is the middle
AgenticMulti-step tasks with tools.
58.3
CodingCode writing and repair.
60.3
ReasoningLogic problems and puzzles.
50.8
MultimodalTasks with images and text.
63.8
KnowledgeFacts and expert knowledge.
56.6
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
60.5
MathMath problems.
55.6

Results

49 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result on the index scale.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
Instruction-Following EvalInstruction94.6%55.1Jeffrey Zhou et al.
MMLU-ReduxKnowledge94.5%53.2Qwen
τ²-Bench Tool-Agent-User EvaluationAgentic93.0%65.5Victor Barres et al.
Harvard-MIT Mathematics Tournament February 2026Math92.9%59.7Qwen
MRCRv2Reasoning91.7%OpenAI
OmniDocBench 1.5Multimodal91.4%OpenAI
MathVisionMultimodal90.3%Qwen
Graduate-Level Google-Proof Q&AKnowledge90.3%61.6David Rein et al.
GPQA DiamondKnowledge90.3%61.6David Rein et al.
Artificial Analysis GPQA DiamondKnowledge90.0%60.8Artificial Analysis
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for CodeCoding89.6%65.8Naman Jain et al.
MMMLUKnowledge89.0%OpenAI
MAXIFEMultilingual88.8%Qwen
Massive Multitask Language Understanding ProfessionalKnowledge88.5%60.0Yubo Wang et al.
Video-MME with subtitleMultimodal88.0%Qwen
MLVU mean averageMultimodal87.4%Qwen
RealWorldQAMultimodal86.9%60.0Qwen
IMOAnswerBenchMath86.0%DeepSeek-AI
CharXiv ReasoningMultimodal85.9%63.9CharXiv authors
VideoMMMUMultimodal85.4%Qwen
MMLU-ProXMultilingual85.4%MMLU-ProX authors
PolyMathMultilingual84.0%Qwen
INCLUDEMultilingual83.0%Qwen
GPQA diamondKnowledge81.8%53.8none effortEpoch AI
SimpleVQAMultimodal81.7%76.1Z.AI
AndroidWorldAgentic81.0%Z.AI
Artificial Analysis MMMU-ProMultimodal80.5%65.5Artificial Analysis
OTIS Mock AIME 2024-2025Math80.0%56.3none effortEpoch AI
Instruction Following BenchmarkInstruction79.1%58.1Benchmark authors
Massive Multi-discipline Multimodal Understanding ProMultimodal79.0%55.9MMMU-Pro authors
ScreenSpot ProMultimodal79.0%60.8Kaixin Li et al.
Artificial Analysis IFBenchInstruction78.0%68.2Artificial Analysis
Software Engineering Benchmark VerifiedCoding77.7%59.9Carlos E. Jimenez et al.
OSWorld-VerifiedAgentic73.3%62.0Tianbao Xie et al.
MCP AtlasAgentic73.2%63.3OpenAI
Artificial Analysis Long Context ReasoningReasoning73.0%58.7Artificial Analysis
Berkeley Function Calling Leaderboard v4Agentic72.9%57.9Arcee AI
SuperGPQA: Scaling LLM Evaluation Across 285 Graduate DisciplinesKnowledge71.4%56.6Xiaoxuan Du et al.
MedXpertQA MultimodalMultimodal71.0%Meta AI
OCRBench V2Multimodal70.7%OCRBench authors
ERQAMultimodal69.8%64.2Qwen
Claw-EvalAgentic62.7%57.0Bowen Ye et al.
DeepPlanningAgentic62.3%DeepPlanning authors
QwenClawBenchAgentic61.8%60.5Qwen
NOVA-63Multilingual58.8%Qwen
SWE-bench ProCoding57.6%59.7Xiang Deng et al.
Artificial Analysis Coding IndexCoding55.9%58.3Artificial Analysis
SkillsBenchCoding54.3%69.0OpenHands11 Sept 2026Vals AI
Terminal-Bench 2.1Agentic52.8%55.221 Sept 2026Vals AI
Scientific Code BenchmarkCoding51.3%61.9Benchmark authors
ODINW13Multimodal51.1%Qwen
Vibe Code Bench v1.1Coding46.4%61.5OpenHands21 Sept 2026Vals AI
Artificial Analysis SciCodeCoding46.1%56.8Artificial Analysis
VITA-BenchAgentic45.6%60.8Meituan LongCat Team
MMSearch-PlusMultimodal41.4%Z.AI
NL2RepoCoding41.1%57.1MiniMax
Artificial Analysis Humanity's Last ExamKnowledge35.6%63.2Artificial Analysis
Humanity's Last ExamKnowledge34.7%58.2Center for AI Safety et al.
FrontierMath-Tiers-1-3-v2-PrivateMath34.4%50.8none effortEpoch AI
Artificial Analysis Intelligence IndexKnowledge25.2%53.9Artificial Analysis
ApexMath22.7%DeepSeek-AI
Artificial Analysis Omniscience AccuracyKnowledge22.5%41.7Artificial Analysis
APEX-Agents-AAAgentic22.4%58.8Artificial Analysis / Mercor
Artificial Analysis Agentic IndexAgentic19.7%53.2Artificial Analysis
Mystery Game PuzzlesReasoning17.0%52.0Epoch AI
Code MigrationCoding12.9%53.121 Sept 2026Vals AI
GDPval-AA normalizedAgentic12.8%45.4Artificial Analysis
Critical Physics TasksReasoning9.1%57.5Artificial Analysis
Chess PuzzlesReasoning9.0%35.2none effortEpoch AI
OSWorld 2.0Agentic2.8%57.3Mengqi Yuan et al.
Agent Arena command recoveryAgentic-4.462.415 Sept 2026LMArena
Agent Arena steerabilityAgentic-5.461.315 Sept 2026LMArena
Agent Arena task outcomeAgentic-7.159.315 Sept 2026LMArena

49 benchmarks count, from 53 of 73 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsOpenRouter, collected directlyNo licence statedEpoch AI, collected directlyCC BY — free to use and redistribute with attributionVals AI, collected directlyNo licence stated. Read from the public leaderboard and credited to Vals AILMArena, collected directlyCC BY 4.0 (lmarena-ai/leaderboard-dataset on Hugging Face)

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free

More from Alibaba

Qwen3.8 Max68.4Qwen3.8-Flash-Next66.4Qwen3.8 Max Preview69.0Qwen3.8-27B63.1Qwen3.7 Max62.6