Grok-3 Mini vs Kimi K2-Thinking-0905: Specs & Benchmark Comparison

CharacteristicGrok-3 MiniKimi K2-Thinking-0905
CompanyxAIMoonshot AI
Release DateFebruary 16, 2025September 4, 2025
Parameters1.0T
MultimodalYesNo
Context (input)128K262K
Context (output)8K66K
Input Price / 1M$0.30$0.60
Output Price / 1M$0.50$2.40
Average Score0.90.9
Benchmarks
AIME 20250.91.0
GPQA0.80.8

Visual Benchmark Comparison

Grok-3 Mini
Kimi K2-Thinking-0905
AIME 20250.9 vs 1.0
0.9
1.0
GPQA0.8 vs 0.8
0.8
0.8

Verdict

Kimi K2-Thinking-0905 leads in 2 out of 4 comparison categories.

Overall Performance

Both models show comparable average scores: Grok-3 Mini — 0.9, Kimi K2-Thinking-0905 — 0.9.

API Cost

Grok-3 Mini is 3.8x cheaper: input $0.30/1M vs $0.60/1M tokens.

Context Window

Kimi K2-Thinking-0905 supports a larger context: 262K vs 128K tokens.

Recency

Kimi K2-Thinking-0905 is newer: released 9/4/2025 vs 2/16/2025.

More About These Models

Related Comparisons

The Grok-3 Mini and Kimi K2-Thinking-0905 comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Grok-3 Mini or Kimi K2-Thinking-0905 page. See also the complete list of AI model comparisons.