Compare models

Context, limits, capabilities, price and use cases side by side — up to 4 models at a time. The URL holds your selection, so you can share it.

Qwen3.8 FlashQwen3.8 MaxQwen3.7 Flash Add a modelChat with these 3

AttributeHide identical rows	Qwen3.8 Flashqwen/qwen3.8-flash	Qwen3.8 Maxqwen/qwen3.8-max	Qwen3.7 Flashqwen/qwen3.7-flash
Specs
Context window	1M	1M	1M
Max output	131K	131K	66K
Input modalities	TextImageVideo	TextImageVideo	TextImageVideo
Output modalities	Text	Text	Text
Capabilities
Streaming	Supported	Supported	Supported
Tool calling	Supported	Supported	Supported
Structured output (JSON)	Supported	Supported	Supported
Image input	Supported	Supported	Supported
Thinking mode	Supported	Supported	Supported
Price / 1M tokens
Input	$ 0.13	$ 1.88	$ 0.040>= 32K$ 0.10>= 256K$ 0.19
Output	$ 0.43	$ 5.63	$ 0.13>= 32K$ 0.37>= 256K$ 0.74
Cache read	$ 0.016	$ 0.23	$ 0.010>= 32K$ 0.020>= 256K$ 0.040
Cache write	$ 0.20	$ 2.35	$ 0.040>= 32K$ 0.12>= 256K$ 0.24
What it is good at
Best for	High-concurrency workloads Coding and cowork agents Million-token context	Maximum reasoning Multimodal coding agents	High-volume agents Visual coding
Published benchmarks
Terminal-Bench 2.1pass_rate	—	86.6%Claude Code · 10 runs(setup not fully disclosed)	—
Agents' Last Examscore	51.2%(setup not fully disclosed)	—	—
DeepSWE 1.1resolved_rate	58.7%(setup not fully disclosed)	—	—
LiveCodeBench v6pass_rate	91.9%(setup not fully disclosed)	—	—
SWE-Bench Multilingualresolved_rate	81%mini-swe-agent(setup not fully disclosed)	—	—
SWE-Bench Proresolved_rate	62.5%Claude Code(setup not fully disclosed)	67.7%Claude Code(setup not fully disclosed)	—
AndroidWorldsuccess_rate	84.5%(setup not fully disclosed)	—	—
OSWorld Verifiedsuccess_rate	—	86.1%(setup not fully disclosed)	—
MRCR v2 256K (8-needle)score	—	92.9%(setup not fully disclosed)	—
CharXiv Reasoning (no tools)accuracy	84.6%(setup not fully disclosed)	—	—
MMMU Proaccuracy	—	82.3%(setup not fully disclosed)	—
Humanity's Last Examaccuracy	35.9%(setup not fully disclosed)	43.6%(setup not fully disclosed)	—
PaperBench (BasicAgent)score	—	93%3 runs(setup not fully disclosed)	—
GPQA Diamondaccuracy	91.7%(setup not fully disclosed)	92.6%(setup not fully disclosed)	—
Toolathlon Verifiedpass_ratesetups differ by: pass_k	73.5%(setup not fully disclosed)	72.5%(setup not fully disclosed)	—
VideoMMMUaccuracy	—	88.7%(setup not fully disclosed)	—