Compare the listed model data for Qwen3 235B-A22B (Jul 25) by Qwen and Qwen3 235B Thinking (Jul 25) by Qwen. Benchmark and pricing records are not a controlled test and may change.
Data last updated: 2026-10-16. Verify current model details with each provider.
What the listed data says
Qwen3 235B-A22B (Jul 25): 128K tokens; Qwen3 235B Thinking (Jul 25): 128K tokens. The listed context-window values are equal. Qwen3 235B-A22B (Jul 25) is listed for no specific capability flags; Qwen3 235B Thinking (Jul 25) is listed for coding, reasoning, long-context tasks. Shared catalog benchmark entries: MMLU: Qwen3 235B-A22B (Jul 25) 93.8%; Qwen3 235B Thinking (Jul 25) 93.0%; AIME 2025: Qwen3 235B-A22B (Jul 25) 85.7%; Qwen3 235B Thinking (Jul 25) 87.0%; LiveCodeBench: Qwen3 235B-A22B (Jul 25) 70.4%; Qwen3 235B Thinking (Jul 25) 72.5%. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
Catalog source links
Use these model and provider links to verify current specifications, pricing, and availability.
The first listed parameter quantities are 235B total (22B active) and 235B total (22B active); the larger quantity is 1× the smaller. Total and active MoE parameters are not directly equivalent.
The catalog release dates are July 2025 and July 2025, about 0 months apart at the precision supplied.
Cost example: 1M input and 1M output tokens
Using only the catalog's listed per-million-token rates, 1M input plus 1M output tokens costs about $2.3 for Qwen3 235B-A22B (Jul 25) and $2.3 for Qwen3 235B Thinking (Jul 25). This excludes provider-specific discounts, caching, and other fees.
Choose Qwen3 235B-A22B (Jul 25) if…
Choose Qwen3 235B-A22B (Jul 25) when your task aligns with catalog-listed uses or strengths such as Production frontier AI with July 2025 instruction improvements, Improved instruction following over April 2025 base release, Same elite benchmark performance, Apache 2.0.
Choose Qwen3 235B Thinking (Jul 25) if…
Choose Qwen3 235B Thinking (Jul 25) when your task aligns with catalog-listed uses or strengths such as Frontier reasoning tasks with July 2025 improvements, Improved thinking mode with July 2025 update, Elite mathematical and reasoning benchmarks, Apache 2.0.
Catalog specifications for Qwen3 235B-A22B (Jul 25) and Qwen3 235B Thinking (Jul 25)
Specification
Qwen3 235B-A22B (Jul 25)
Qwen3 235B Thinking (Jul 25)
Provider
Qwen
Qwen
Parameters
235B total (22B active)
235B total (22B active)
Context window
128K tokens
128K tokens
Maximum output
Not listed
Not listed
Catalog pricing
Apache 2.0 — free
Apache 2.0 — free
Listed input/output cost per 1M tokens
input $0.8, output $1.5 per 1M tokens
input $0.8, output $1.5 per 1M tokens
License
Apache 2.0
Apache 2.0
Coding support
Not listed
Listed
Reasoning support
Not listed
Listed
Vision input
Not listed
Not listed
Multimodal
Not listed
Not listed
Open weights
Yes
Yes
Benchmark: MMLU
93.8%
93.0%
Benchmark: AIME 2025
85.7%
87.0%
Benchmark: LiveCodeBench
70.4%
72.5%
Figures are transcribed from LITHOVEX model records. Benchmark versions and evaluation setups may differ; pricing and specifications can change. Check each provider's current documentation before making a decision.
Frequently Asked Questions
What is different between Qwen3 235B-A22B (Jul 25) and Qwen3 235B Thinking (Jul 25)?
Qwen3 235B-A22B (Jul 25): 128K tokens; Qwen3 235B Thinking (Jul 25): 128K tokens. The listed context-window values are equal. Qwen3 235B-A22B (Jul 25) is listed for no specific capability flags; Qwen3 235B Thinking (Jul 25) is listed for coding, reasoning, long-context tasks. Shared catalog benchmark entries: MMLU: Qwen3 235B-A22B (Jul 25) 93.8%; Qwen3 235B Thinking (Jul 25) 93.0%; AIME 2025: Qwen3 235B-A22B (Jul 25) 85.7%; Qwen3 235B Thinking (Jul 25) 87.0%; LiveCodeBench: Qwen3 235B-A22B (Jul 25) 70.4%; Qwen3 235B Thinking (Jul 25) 72.5%. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
What benchmark values are listed for Qwen3 235B-A22B (Jul 25) and Qwen3 235B Thinking (Jul 25)?
MMLU: Qwen3 235B-A22B (Jul 25) 93.8%; Qwen3 235B Thinking (Jul 25) 93.0%; AIME 2025: Qwen3 235B-A22B (Jul 25) 85.7%; Qwen3 235B Thinking (Jul 25) 87.0%; LiveCodeBench: Qwen3 235B-A22B (Jul 25) 70.4%; Qwen3 235B Thinking (Jul 25) 72.5%. The catalog values may use different versions and evaluation setups, so they are reference points rather than a controlled head-to-head result.
Which model has the larger listed context window?
Qwen3 235B-A22B (Jul 25): 128K tokens; Qwen3 235B Thinking (Jul 25): 128K tokens. The listed context-window values are equal.
What are the listed costs per million tokens for Qwen3 235B-A22B (Jul 25) and Qwen3 235B Thinking (Jul 25)?
Qwen3 235B-A22B (Jul 25): input $0.8, output $1.5 per 1M tokens (Apache 2.0 — free). Qwen3 235B Thinking (Jul 25): input $0.8, output $1.5 per 1M tokens (Apache 2.0 — free). Where separate numeric input and output rates are available, the worked example uses 1M input plus 1M output tokens. Confirm current terms with each provider.
How far apart are the listed release dates for Qwen3 235B-A22B (Jul 25) and Qwen3 235B Thinking (Jul 25)?
The catalog lists Qwen3 235B-A22B (Jul 25) as July 2025 and Qwen3 235B Thinking (Jul 25) as July 2025, about 0 months apart at the precision supplied.
When was the comparison data last updated?
The model catalog records 2026-10-16 as its data update date. Provider specifications and prices may have changed since then.
How should I choose between Qwen3 235B-A22B (Jul 25) and Qwen3 235B Thinking (Jul 25)?
Compare the listed specifications and capabilities, review the benchmark notes, then test both with the same representative prompt for your task. This page does not claim a universal winner.
Create your free LITHOVEX account and compare Qwen3 235B-A22B (Jul 25) and Qwen3 235B Thinking (Jul 25) on your actual tasks. No credit card, no API key, no subscriptions needed.