AI Model Release Tracker - Timeline of Major AI Models from 2022-2026

Claude Sonnet 5 vs Kimi K3

Anthropic
Claude Sonnet 5
Moonshot AI
Kimi K3
Overview
CompanyAnthropicMoonshot AI
Release dateJun 30 2026Jul 16 2026
AccessProprietaryOpen Weight
Specifications
Parameters
2.8T
Context window
1M
Benchmarks
Nonsense detection
BullshitBench v2
80%
Agentic coding
SWE-Bench Pro
63.2%
Agentic coding
CursorBench v3.1
61.2%
Agentic coding
DeepSWE 1.0
67.5%
Agentic terminal coding
Terminal-Bench 2.1
80.4%
88.3%Best
Multi-step tool use
MCP Atlas
84.2%
Professional tool use
JobBench
52.9%
Personal tool use
Toolathlon-Verified
73.2%
Web browsing
BrowseComp
84.7%
91.2%Best
Multidisciplinary reasoning
Humanity's Last Exam · no tools
43.2%
43.5%Best
Multidisciplinary reasoning
Humanity's Last Exam · with tools
57.4%Best
56%
Science
GPQA Diamond
93.5%
Agentic computer use
OSWorld-Verified
81.2%
Knowledge work
GDPval-AA
1618
Knowledge work
GDPval-AA v2
1668
Chart reasoning
CharXiv Reasoning
84.8%
Multimodal reasoning
MMMU-Pro
81.6%
Community preference (code)
Arena Elo (Code)
1543
Timeline
Release gapClaude Sonnet 5 shipped 16 days before Kimi K3

Which is better: Claude Sonnet 5 or Kimi K3?

Kimi K3 leads Claude Sonnet 5 on 3 of the 4 benchmarks they both report (Terminal-Bench 2.1, BrowseComp, Humanity's Last Exam). Claude Sonnet 5 shipped 16 days before Kimi K3, so benchmark comparisons should account for the intervening progress.

Claude Sonnet 5 is proprietary, while Kimi K3 is open weight.

On Terminal-Bench 2.1, Kimi K3 leads at 88.3% vs Claude Sonnet 5 at 80.4%. On BrowseComp, Kimi K3 leads at 91.2% vs Claude Sonnet 5 at 84.7%. On Humanity's Last Exam · no tools, Kimi K3 leads at 43.5% vs Claude Sonnet 5 at 43.2%. On Humanity's Last Exam · with tools, Claude Sonnet 5 leads at 57.4% vs Kimi K3 at 56%.

Frequently asked questions

Claude Sonnet 5 was released by Anthropic on Jun 30 2026.

Kimi K3 was released by Moonshot AI on Jul 16 2026.

Kimi K3 leads on Terminal-Bench 2.1 — Claude Sonnet 5 80.4% vs Kimi K3 88.3%.

Kimi K3 leads on Humanity's Last Exam · no tools — Claude Sonnet 5 43.2% vs Kimi K3 43.5%.

Claude Sonnet 5 is a proprietary model released by Anthropic. Kimi K3 is an open weight model released by Moonshot AI.

Other comparisons