Coding Agent Index
46.9 score
LLM Leaderboard · Open Weight
Kimi K2.7 Code benchmarks, pricing, and LLM comparison.
Compare Kimi K2.7 Code vs GPT, Claude, Gemini, DeepSeek, open-weight, and frontier AI models using public benchmark scores, token pricing, context window, and access details.
Rank #7AskClash overall score: 69.0
$0.95 / $4.00Input and output token price, when published. Context: 256K.
APIBilling and access path cached for this model row.
Kimi K2.7 Code benchmark snapshot
AskClash combines public LLM benchmark cells into a weighted percentile score and penalizes missing coverage so narrow rows do not dominate better-measured models.
Overall69.0
Benchmark cells13
Context256K
CreatorMoonshot AI
Kimi K2.7 Code public benchmark scores
Cached benchmark values can include HLE, GPQA, SWE-bench, SWE-Pro, SWE-Atlas, Terminal-Bench, MCP Atlas, MMMU-Pro, ARC-AGI-2, Tau2, and model-specific coding or agent scores.
HLE
54.0 score
GPQA
90.5 score
SWE-bench
80.2 score
SWE-Pro
58.6 score
Terminal-Bench
66.7 score
LiveCodeBench
89.6 score
OSWorld
73.1 score
MCP Atlas
76.0 score
Finance Agent
44.9 score
CharXiv
80.4 score
MMMU-Pro
79.4 score
Tau2
95.9 score
Kimi K2.7 Code vs other AI models
Use these comparison links to evaluate Kimi K2.7 Code against nearby LLMs by benchmark score, price, context window, and provider.
Kimi K2.7 Code vs Claude Mythos/Fable 5Kimi K2.7 Code vs Claude Opus 4.8 (Adaptive)Kimi K2.7 Code vs GPT-5.5 xHighKimi K2.7 Code vs Claude Opus 4.7 (Adaptive)Kimi K2.7 Code vs GPT-5.4 xHighKimi K2.7 Code vs Gemini 3.5 Flash HighKimi K2.7 Code vs Gemini 3.1 ProKimi K2.7 Code vs Claude Opus 4.6 (Adaptive)
Related AI and tech coverage
Cached AskClash article matches that can provide release, provider, benchmark, pricing, or market context around this model.
AgentFlow: Orchestrate Claude, Codex, and Kimi Agents in Dependency Graphs
AgentFlow orchestrates coding agents (Claude Code, OpenAI Codex, Kimi) as nodes in DAG pipelines with parallel fanout, iterative cycles, and remote execution on SSH/EC2/ECS. 697 stars, Python 3.11+.
Kimi K2.6 🚀, Codex Chronicle 🤖, Bezos’ $10B AI fundraise 💰
TLDR AI
AgentFlow specs.py — Core Data Models (Pydantic Specs for Pipelines, Nodes, Agents)
Pydantic data models defining AgentFlow's type system: AgentKind (codex/claude/kimi/python/shell/sync), NodeSpec, PipelineSpec, ProviderConfig, target types (local/SSH/EC2/ECS/container), fanout expansion, MCP server specs.
AgentFlow DSL — Python Domain-Specific Language for Building Agent Pipelines
Python DSL for constructing AgentFlow pipelines. Graph/DAG container, NodeBuilder with >> operator for dependencies, fanout()/merge() for parallel expansion, convenience functions claude()/codex()/kimi()/python_node()/shell().
Last cached leaderboard date: June 12, 2026. This model page is generated from the AskClash LLM Leaderboard cache and linked from the live leaderboard.