DeepSeek-R1-0528 vs Qwen3-235B-A22B-Thinking-2507
DeepSeek-R1-0528 and Qwen3-235B-A22B-Thinking-2507 are closely matched at 24.1 and 28.1 on the LLM Stats Score. DeepSeek-R1-0528 is 1.1x cheaper per token.
DeepSeek · Alibaba Cloud / Qwen Team · Updated for 2026
Which is better?
DeepSeek-R1-0528 and Qwen3-235B-A22B-Thinking-2507 are closely matched on the overall LLM Stats Score at 24.1 and 28.1.
In the 5 individual benchmarks reported for both models, Qwen3-235B-A22B-Thinking-2507 wins 4; this is a narrower head-to-head signal than the composite indexes.
On price, DeepSeek-R1-0528 is roughly 1.1x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Qwen3-235B-A22B-Thinking-2507 also accepts a larger context window (262,144 input tokens), making it the stronger choice for long documents and large codebases.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose DeepSeek-R1-0528
- cost matters — it's about 1.1x cheaper per token
Choose Qwen3-235B-A22B-Thinking-2507
- your work emphasizes agents — it leads those capability indexes
- you value its reported benchmark strengths — it wins 4 of 5 exact shared results
- you process long inputs — it offers a 262,144 token context window
- you want the most recent training data — it shipped Jul 2025
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
16 reported for DeepSeek-R1-0528 · 25 for Qwen3-235B-A22B-Thinking-2507
DeepSeek-R1-0528 outperforms in 1 benchmarks (MMLU-Pro), while Qwen3-235B-A22B-Thinking-2507 is better at 4 benchmarks (AIME 2025, GPQA, Humanity's Last Exam, MMLU-Redux).
Qwen3-235B-A22B-Thinking-2507 significantly outperforms across most benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, DeepSeek-R1-0528 ($0.50/1M tokens) is 1.7x more expensive than Qwen3-235B-A22B-Thinking-2507 ($0.30/1M tokens).
For output processing, DeepSeek-R1-0528 ($2.15/1M tokens) is 1.4x cheaper than Qwen3-235B-A22B-Thinking-2507 ($3.00/1M tokens).
In conclusion, Qwen3-235B-A22B-Thinking-2507 is more expensive than DeepSeek-R1-0528.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
DeepSeek-R1-0528 has 436.0B more parameters than Qwen3-235B-A22B-Thinking-2507, making it 185.5% larger.
Context Window
Maximum input and output token capacity
Qwen3-235B-A22B-Thinking-2507 accepts 262,144 input tokens compared to DeepSeek-R1-0528's 163,840 tokens. DeepSeek-R1-0528 can generate longer responses up to 163,840 tokens, while Qwen3-235B-A22B-Thinking-2507 is limited to 131,072 tokens.
License
Usage and distribution terms
DeepSeek-R1-0528 is licensed under MIT, while Qwen3-235B-A22B-Thinking-2507 uses Apache 2.0.
License differences may affect how you can use these models in commercial or open-source projects.
MIT
Open weights
Apache 2.0
Open weights
Release Timeline
When each model was launched
DeepSeek-R1-0528 was released on 2025-05-28, while Qwen3-235B-A22B-Thinking-2507 was released on 2025-07-25.
Qwen3-235B-A22B-Thinking-2507 is 2 months newer than DeepSeek-R1-0528.
May 28, 2025
1.3 years ago
Jul 25, 2025
1.1 years ago
1mo newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
DeepSeek-R1-0528 is available from DeepInfra, DeepSeek, Novita. Qwen3-235B-A22B-Thinking-2507 is available from Fireworks, Novita.
DeepSeek-R1-0528
Qwen3-235B-A22B-Thinking-2507
Outputs Comparison
Judge for yourself.
Run your own prompts against DeepSeek-R1-0528 and Qwen3-235B-A22B-Thinking-2507 side-by-side, then vote on the output you prefer.
FAQ
Common questions about DeepSeek-R1-0528 vs Qwen3-235B-A22B-Thinking-2507.