Kimi K2-Thinking-0905 vs Sakana Namazu: Specs & Benchmark Comparison

Kimi K2-Thinking-0905 is developed by Moonshot AI, while Sakana Namazu comes from Sakana AI. Kimi K2-Thinking-0905 was released in September 2025, and Sakana Namazu followed 11 months later in August 2026. Kimi K2-Thinking-0905 has a published size of about 1.0 trillion parameters; Sakana AI has not disclosed the parameter count of Sakana Namazu.

The two models share 2 published benchmarks. Sakana Namazu leads on 2 of them. The widest gaps are on LiveCodeBench v6, where Sakana Namazu scores 90.3% against 83.1%; MMLU-Pro, where Sakana Namazu scores 90.3% against 85.0%. Averaged across everything we track, Kimi K2-Thinking-0905 sits at 68.3% and Sakana Namazu at 92.4%.

Kimi K2-Thinking-0905 is the cheaper API at $0.60 per million input tokens and $2.40 per million output tokens, about 58% below Sakana Namazu at $0.95 and $4. Both accept a context window of about 256K tokens. Kimi K2-Thinking-0905 accepts text as input, while Sakana Namazu accepts text and images. On tooling, only Kimi K2-Thinking-0905 supports function calling and only Kimi K2-Thinking-0905 offers structured output.

CharacteristicKimi K2-Thinking-0905Sakana Namazu
CompanyMoonshot AISakana AI
Release DateSeptember 4, 2025August 3, 2026
Parameters1.0T
MultimodalNoYes
Context (input)262K256K
Context (output)66K256K
Input Price / 1M$0.60$0.95
Output Price / 1M$2.40$4.00
Average Score68.3%92.4%
Benchmarks
LiveCodeBench v683.1%90.3%
MMLU-Pro85.0%90.3%

Visual Benchmark Comparison

Kimi K2-Thinking-0905
Sakana Namazu
LiveCodeBench v60.8 vs 0.9
0.8
0.9
MMLU-Pro0.8 vs 0.9
0.8
0.9

Verdict

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

Overall Performance

Both models show comparable average scores: Kimi K2-Thinking-0905 — 0.7, Sakana Namazu — 0.9.

API Cost

Kimi K2-Thinking-0905 is 1.6x cheaper: input $0.60/1M vs $0.95/1M tokens.

Context Window

Kimi K2-Thinking-0905 supports a larger context: 262K vs 256K tokens.

Recency

Sakana Namazu is newer: released 8/3/2026 vs 9/4/2025.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — Kimi K2-Thinking-0905 or Sakana Namazu?
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 Sakana Namazu?
Kimi K2-Thinking-0905 is cheaper for input: $0.60 per 1M tokens vs $0.95.
Which has a larger context window — Kimi K2-Thinking-0905 or Sakana Namazu?
Kimi K2-Thinking-0905 supports a larger context: 262,144 tokens vs 256,000.

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