Qwen3.7 Max vs GLM 5.2

At a Glance

Compare
Intelligence, Cost, and Efficiency
IntelligenceHigher is better · MM Intelligence v2.5UnrankedNot in the 46-model eligible cohort#23 of 4661.9 score · 2/3 sources · provisional · missing ARC-AGI-2 · full-core range 41.3–74.6
CostLower is better · Published-token output estimate#13 of 44$0.057 per LiveBench case#12 of 44$0.056 per LiveBench case
EfficiencyHigher is better · MM Efficiency v1.5UnrankedNot in the 38-model eligible cohort#7 of 3861.3 score · 2/3 sources · provisional · missing ARC-AGI-2 · full-core range 51.0–67.6
Pricing and Limits
Input priceFrom · USD / 1M tokens$1.475Openrouter · Sep 23, 2026$0.75Deepinfra · Sep 23, 2026
Output priceFrom · USD / 1M tokens$4.425Openrouter · Sep 23, 2026$2.40Deepinfra · Sep 23, 2026
Context windowMaximum documented tokens1,000K1,049K
Model facts checkedSep 3, 2026View model evidence →Aug 28, 2026View model evidence →

Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →

Available Benchmarks

All benchmark results →
BenchmarkQwen3.7 MaxGLM-5.2
LMArena Agent Arenaagent-2026-09-15-d25aabda0010 · outcome_score · leader-3.6392% of row best · score · Qwen3.7 Max; 95% CI [-4.47002493, -2.78058186]; sessions 38392; observations 1816729; rank 344.37100% of row best · score · GLM 5.2 (Max); 95% CI [3.67608698, 5.05982987]; sessions 76766; observations 4943866; rank 14
LiveBench2026-06-25 · overall · leader77.50100% of row best · percent · qwen3.7-max · 12,909 output tokens / case76.9699% of row best · percent · glm-5.2 · 23,463 output tokens / case
ToneBench2026-09-11-10-task-4ef099199c9c · overall_score · unverified81.2699% of row best · points · Qwen3.7 Max (default) · 8,636 output tokens / case82.14100% of row best · points · GLM-5.2 · 5,633 output tokens / case
Overall ResultCounted from the protocol-matched rows above1 benchmark winNo overall winner1 benchmark winNo overall winner

Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.

Side-by-Side Facts

FieldQwen3.7 MaxGLM-5.2
DeveloperQwenZ.ai
FamilyQwen3 7Glm 5 2
ModelQwen3.7 MaxGLM-5.2
VersionQwen3.7 MaxGLM-5.2
Lifecycleactiveactive
Released2026-05-20Unknown
Knowledge cutoffUnknownUnknown
Input modalitiesText, Image, VideoText
Output modalitiesTextText
Context window1,000K1,049K
Total parametersUnknown753.3B
Active parametersUnknownUnknown
LicenseUnknownmit
Open weightsNoYes
API availableYesYes
Self-hostableNoYes
Provider accessAlibaba Cloud Model Studio (Standard), Deepinfra (Standard), Openrouter (Standard), Together Ai (Standard)Deepinfra (Standard), Fireworks Ai (Standard), Hugging Face (Standard), Openrouter (Standard), Together Ai (Standard)
Capabilitiesagents, chat, generation, reasoning, structured_outputs, tools, visionchat, generation, reasoning, tools

Qwen3.7 Max Capabilities

agentschatgenerationreasoningstructured outputstoolsvision
Serving providers4
Canonical IDqwen/qwen3.7-max

GLM 5.2 Capabilities

chatgenerationreasoningtools
Serving providers5
Canonical IDzai-org/GLM-5.2

Primary Evidence

Sources and Freshness

Questions

Qwen3.7 Max vs GLM 5.2 FAQs

Is Qwen3.7 Max or GLM 5.2 better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Qwen3.7 Max and GLM 5.2, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Qwen3.7 Max or GLM 5.2?+

Qwen3.7 Max is $1.475 and GLM 5.2 is $0.75 per million tokens, so GLM 5.2 is cheaper on this metric. Qwen3.7 Max is $4.425 and GLM 5.2 is $2.40 per million tokens, so GLM 5.2 is cheaper on this metric.

Which has a larger context window, Qwen3.7 Max or GLM 5.2?+

GLM 5.2 has the larger sourced context window. Qwen3.7 Max supports 1,000K and GLM 5.2 supports 1,049K.

Which performs better in benchmarks, Qwen3.7 Max or GLM 5.2?+

There is no overall benchmark winner: The verified common benchmarks do not produce a majority winner.

Can Qwen3.7 Max or GLM 5.2 be self-hosted?+

GLM 5.2 is the only model in this pair currently marked as self-hostable. Qwen3.7 Max is not marked open weight; GLM 5.2 is open weight.

Can Qwen3.7 Max and GLM 5.2 understand images?+

Qwen3.7 Max is documented with image input; GLM 5.2 is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Qwen3.7 Max or GLM 5.2?+

Neither has a larger sourced maximum output. Qwen3.7 Max is 66K and GLM 5.2 is —.

Do Qwen3.7 Max and GLM 5.2 support reasoning and tool use?+

Qwen3.7 Max: reasoning, tool calling, and image input. GLM 5.2: reasoning and tool calling. Feature support does not establish relative quality.

Which is available from more inference providers, Qwen3.7 Max or GLM 5.2?+

Qwen3.7 Max has 4 sourced provider routes; GLM 5.2 has 5, so GLM 5.2 has broader tracked availability.

Which offers better value, Qwen3.7 Max or GLM 5.2?+

There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.

Send Feedback