VerdictPal
Join

Models / Alibaba

Qwen3.7 Max

Qwen3.7 Max · Released 2026-05-19

AA Intelligence Index 46.0. Listed on Artificial Analysis with API pricing $2.5/$7.5 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#12 of 51 on AA Index · current snapshot
46 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite58
Context128K
Input / 1M$2.5
Output / 1M$7.5
Knowledge cutoffopen
Output speed207 t/s
TTFT (default API)1.55s
Statussolid
ReasoningCodingAgenticLong context
Reasoning
92
Coding
49
Agentic
75
Long context
69

71average across 4 tested families

Benchmark placements

Where Qwen3.7 Max places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
IFBenchReasoning#5/ 5781Artificial Analysis2026-07-21
AA output speedPerformance#10/ 69Artificial Analysis2026-07-21
GPQA DiamondReasoning#11/ 6992Artificial Analysis2026-07-21
Terminal-BenchAgentic#18/ 6975Artificial Analysis2026-07-21
Artificial Analysis Intelligence IndexReasoning#19/ 6746Artificial Analysis2026-07-21
Humanity's Last ExamReasoning#20/ 6538Artificial Analysis2026-07-21
AA-LCRLong context#28/ 6469Artificial Analysis2026-07-21
SciCodeCoding#32/ 6549Artificial Analysis2026-07-21
AA time to first tokenPerformance#34/ 69Artificial Analysis2026-07-21
τ³-Bench BankingAgentic#56/ 6411Artificial Analysis2026-07-21
Family context

The three highest-scoring carded models in each capability family. Where Qwen3.7 Max shows up, it's highlighted.

ReasoningQwen3.7 Max · 92
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
CodingQwen3.7 Max · 49
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticQwen3.7 Max · 75
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextQwen3.7 Max · 69
  1. 1
    Kimi K3
    75
  2. 2
    GPT-5.1
    75
  3. 3
    GPT-5.6 Sol
    74
Newest receipts

Benchmark rows added to the public ledger for Qwen3.7 Max in the last 120 days. Older rows live in the full table below.

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context69%Artificial Analysis2
AA output speedPerformance207 t/sArtificial Analysis2
AA time to first tokenPerformance1.55sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning46%Artificial Analysis2
GPQA DiamondReasoning92.3%Artificial Analysis2
Humanity's Last ExamReasoning38.1%Artificial Analysis2
IFBenchReasoning80.54%Artificial Analysis2
SciCodeCoding48.8%Artificial Analysis2
τ³-Bench BankingAgentic10.93%Artificial Analysis2
Terminal-BenchAgentic74.53%Artificial Analysis2
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning92
Coding49
Agentic75
Long context69
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMiniMaxxAIMetaZhipuXiaomiMeituanCohere

Full benchmark ledger

Every catalog benchmark for Qwen3.7 Max. Scores link to the original source; gaps mean no public row exists yet.

10 sourced rows

10 of 32 catalog benchmarks have a sourced row for Qwen3.7 Max.

Reasoning

Coding

Agentic

Long context

Performance

Sources