Moonshot AI (Kimi)Kimi K2.7 CodeVSOpenAIGPT-5.4 mini
Our Take
We recommend Kimi K2.7 Code for its clear benchmark advantage, or the 1.0x cheaper GPT-5.4 mini only if your budget requires optimizing costs for very high-volume pipelines. While Kimi K2.7 Code offers superior reasoning and coding, it carries a moderate price premium. Choose Kimi K2.7 Code for quality, or GPT-5.4 mini for cost optimization.
▶WHY?
Benchmark Calculations & Evidence:
Coding Benchmarks: Both models were evaluated on the SWE-bench Pro benchmark. Kimi K2.7 Code scored 58.6%, while GPT-5.4 mini scored 54.4%.
Reasoning Benchmarks: Both models were evaluated on the GPQA Diamond benchmark. Kimi K2.7 Code scored 90%, while GPT-5.4 mini scored 87.5%.
Cost Efficiency: GPT-5.4 mini pricing ($0.75/M input, $4.5/M output) is 1.0x cheaper than Kimi K2.7 Code ($0.95/M input, $4/M output).
Was this recommendation helpful?
Benchmarks & Scores
Coding (swe-bench-pro)Winner (+4.2%)
58.6%complex codebases, multi-file repositories, and architectural planning
Reasoning (gpqa-diamond)Winner (+2.5%)
90%graduate-level science QA
Cost & Context
Cost (per 1M tokens)
$1.71Input: $0.95 | Output: $4.00Context Window
262.14k tokensBenchmarks & Scores
Coding (swe-bench-pro)
54.4%complex codebases, multi-file repositories, and architectural planning
Reasoning (gpqa-diamond)
87.5%graduate-level science QA
Cost & Context
Cost (per 1M tokens)
$1.69Input: $0.75 | Output: $4.50Context WindowLarger
400k tokensFrequently Asked Questions about Kimi K2.7 Code vs GPT-5.4 mini
GPT-5.4 mini is cheaper than Kimi K2.7 Code. GPT-5.4 mini has a blended cost of $1.69/1M tokens, which is about 1.0x cheaper than Kimi K2.7 Code at $1.71/1M tokens.
Kimi K2.7 Code is better for coding tasks on this benchmark. It scores 58.6% on swe-bench-pro (complex codebases, multi-file repositories, and architectural planning) compared to GPT-5.4 mini which scores 54.4%.
Related Matchups
Explore similar comparisons for Kimi K2.7 Code and GPT-5.4 mini.
Do you want to find a model for your constraints?
Use our interactive model finder to filter LLMs by reasoning capability, coding performance, cost, and context length.