Qwen3-235B-A22B-Thinking-2507 vs Step-3.5-Flash: Specs & Benchmark Comparison

CharacteristicQwen3-235B-A22B-Thinking-2507Step-3.5-Flash
CompanyAlibabaStepFun
Release DateJuly 24, 2025February 1, 2026
Parameters235B196B
MultimodalNoYes
Context (input)256K66K
Context (output)131K8K
Input Price / 1M$0.30$0.10
Output Price / 1M$3.00$0.40
Average Score0.90.8
Benchmarks
AIME 20250.91.0

Visual Benchmark Comparison

Qwen3-235B-A22B-Thinking-2507
Step-3.5-Flash
AIME 20250.9 vs 1.0
0.9
1.0

Verdict

Step-3.5-Flash leads in 2 out of 4 comparison categories.

Overall Performance

Both models show comparable average scores: Qwen3-235B-A22B-Thinking-2507 — 0.9, Step-3.5-Flash — 0.8.

API Cost

Step-3.5-Flash is 6.6x cheaper: input $0.10/1M vs $0.30/1M tokens.

Context Window

Qwen3-235B-A22B-Thinking-2507 supports a larger context: 256K vs 66K tokens.

Recency

Step-3.5-Flash is newer: released 2/1/2026 vs 7/24/2025.

More About These Models

Related Comparisons

The Qwen3-235B-A22B-Thinking-2507 and Step-3.5-Flash comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Qwen3-235B-A22B-Thinking-2507 or Step-3.5-Flash page. See also the complete list of AI model comparisons.