Kimi K2-Thinking-0905 vs MiniMax M2: Specs & Benchmark Comparison

CharacteristicKimi K2-Thinking-0905MiniMax M2
CompanyMoonshot AIMiniMax
Release DateSeptember 4, 2025October 26, 2025
Parameters1.0T230B
MultimodalNoNo
Context (input)262K1.0M
Context (output)66K100K
Input Price / 1M$0.60$1.00
Output Price / 1M$2.40$4.00
Average Score0.90.8
Benchmarks
AIME 20251.00.8
GPQA0.80.8
MMLU-Pro0.80.8

Visual Benchmark Comparison

Kimi K2-Thinking-0905
MiniMax M2
AIME 20251.0 vs 0.8
1.0
0.8
GPQA0.8 vs 0.8
0.8
0.8
MMLU-Pro0.8 vs 0.8
0.8
0.8

Verdict

MiniMax M2 leads in 2 out of 4 comparison categories.

Overall Performance

Both models show comparable average scores: Kimi K2-Thinking-0905 — 0.9, MiniMax M2 — 0.8.

API Cost

Kimi K2-Thinking-0905 is 1.7x cheaper: input $0.60/1M vs $1.00/1M tokens.

Context Window

MiniMax M2 supports a larger context: 1M vs 262K tokens.

Recency

MiniMax M2 is newer: released 10/26/2025 vs 9/4/2025.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — Kimi K2-Thinking-0905 or MiniMax M2?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — Kimi K2-Thinking-0905 or MiniMax M2?
Kimi K2-Thinking-0905 is cheaper for input: $0.60 per 1M tokens vs $1.00.
Which has a larger context window — Kimi K2-Thinking-0905 or MiniMax M2?
MiniMax M2 supports a larger context: 1,000,000 tokens vs 262,144.

The Kimi K2-Thinking-0905 and MiniMax M2 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 MiniMax M2 page. See also the complete list of AI model comparisons.