Skip to content
gentic.news — AI News Intelligence Platform
Connecting to the Living Graph…
Coding-focusedOpen Source#4 of 9 in category

Kimi K2.6

Moonshot AI · Launched Apr 2026

Moonshot's open agentic model; SWE-bench Verified 80.2%, SWE-bench Pro 58.6%, Terminal-Bench 2.0 66.7%. Sustains 4,000+ tool calls over 13-hour sessions.

4
Benchmarks scored
80.2
Peak score
4
Article mentions
Yes
Open source

Benchmark performance

SWE-Bench Verified

OpenAI-verified 500-issue subset of SWE-Bench. Approaching saturation in 2026 - most frontier models clear 80%+.

80.2
Gap to SOTA: -14.8pp (held by Claude Fable 5)Benchmark docs →
Terminal-Bench 2.1

Held-out, contamination-resistant CLI tasks driven end-to-end in a real terminal. Version 2.1 is the 2026 standard for terminal autonomy.

66.7
Gap to SOTA: -16.7pp (held by Codex CLI (GPT-5.5))Benchmark docs →
SWE-Bench Pro

Harder, contamination-resistant successor to SWE-Bench Verified: real GitHub issues with held-out tests. Where coding headroom remains.

58.6
Gap to SOTA: -10.6pp (held by Claude Opus 4.8)Benchmark docs →

Other coding-focused agents

The 9 agents in this category, ranked by peak benchmark.

AgentMakerLaunchPeakPricing
Kimi K2.5OSSMoonshot AI2026-011410.0Open weights
Claude CodeAnthropic2025-0288.6Claude Max / API
Codex CLIOpenAI2025-0483.4ChatGPT / API
SWE-AgentOSSPrinceton + Stanford2024-0474.0Open source (MIT)
Gemini CLIOSSGoogle2025-0670.7Free tier + API
GLM-5.1OSSZ.ai2026-0458.4Open weights
OpenCodeOSSOpenCode2025-06Open source
AiderOSSAider2023-05Open source (Apache-2)

Recent coverage

Quick facts

Type
Coding-focused
Maker
Moonshot AI
Launch
2026-04-01
Open source
Yes
Pricing
Open weights
Benchmarks scored
4
Article mentions
4
Rank in category
#4 of 9