Preseason
MatchesRankingsPrompts
GitHub
Preseason
MatchesRankingsPromptsMethodologyContact

© 2026 Preseason. All rights reserved.

PrivacyTerms
@betocmn
AI / LLM Integration
Methodology

Intercom vs Claude Code

INIntercomvsClaude CodeCLClaude Code
IntercomClaude Code
49%
51%

Leading: Claude Code (51.2%)

Statistics

MetricValue
Intercom wins99
Claude Code wins104
Abstains (no tool)19
Other tool chosen2379
Decisive cases203
Intercom win rate (unweighted)48.8%
95% CI42.0% - 55.6%
Intercom win rate (weighted)48.8%

Comments

Intercom

No comments yet

Verified critics can leave comments here.

Claude Code

No comments yet

Verified critics can leave comments here.

Per-model breakdown

ModelTierIntercomClaude CodeNoneOtherA rate
MiniMax M2.7Frontier84506715%
Claude Haiku 4.5Small424011214%
DeepSeek V3.2Mid1314010448%
Llama 4 ScoutSmall2002114100%
Mistral Small 4Mid140293100%
GLM 5 TurboFrontier01421150%
Claude Sonnet 4.6Frontier1300128100%
GPT 5.4Frontier900123100%
GPT 5.4 MiniMid701133100%
Llama 4 MaverickFrontier503128100%
MiniMax M3Frontier05040%
MiMo V2 ProFrontier200128100%
DeepSeek R1 0528Frontier102135100%
DeepSeek V4 FlashMid1008100%
Gemini 2.5 ProFrontier102138100%
Kimi K2.5Frontier101116100%
GPT 5.3 CodexFrontier0101400%
MiMo V2.5 ProFrontier01080%
Claude Opus 4.6Frontier000132n/a
Claude Opus 4.8Frontier0008n/a
DeepSeek V4 ProFrontier0018n/a
Devstral 2 2512Mid002135n/a
Gemini 2.5 FlashSmall000132n/a
Gemini 3.5 FlashSmall0008n/a
GLM 5.2Frontier0009n/a
GPT 5.5Frontier0007n/a
Kimi K2.7 CodeFrontier0009n/a
Qwen3 Coder NextMid001137n/a

Per-prompt breakdown

PromptTierIntercomClaude CodeNoneOtherA rate
ai-support-agent-platformBeginner995131395%
ai-revenue-ops-copilotBeginner02903780%
ai-revenue-ops-copilotAdvanced02833910%
ai-support-agent-platformAdvanced01714130%
ai-revenue-ops-copilotIntermediate01414170%
ai-support-agent-platformIntermediate0704270%
ai-agent-applicationAdvanced023150%
ai-agent-applicationIntermediate015110%
ai-agent-applicationBeginner015140%