Kimi K2-Thinking-0905 vs Step-3.5-Flash: Specs & Benchmark Comparison

CharacteristicKimi K2-Thinking-0905Step-3.5-Flash
CompanyMoonshot AIStepFun
Release DateSeptember 4, 2025February 1, 2026
Parameters1.0T196B
MultimodalNoYes
Context (input)262K66K
Context (output)66K8K
Input Price / 1M$0.60$0.10
Output Price / 1M$2.40$0.40
Average Score0.90.8
Benchmarks
AIME 20251.01.0

Visual Benchmark Comparison

Kimi K2-Thinking-0905
Step-3.5-Flash
AIME 20251.0 vs 1.0
1.0
1.0

Verdict

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

Overall Performance

Both models show comparable average scores: Kimi K2-Thinking-0905 — 0.9, Step-3.5-Flash — 0.8.

API Cost

Step-3.5-Flash is 6.0x cheaper: input $0.10/1M vs $0.60/1M tokens.

Context Window

Kimi K2-Thinking-0905 supports a larger context: 262K vs 66K tokens.

Recency

Step-3.5-Flash is newer: released 2/1/2026 vs 9/4/2025.

More About These Models

Related Comparisons

The Kimi K2-Thinking-0905 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 Kimi K2-Thinking-0905 or Step-3.5-Flash page. See also the complete list of AI model comparisons.