Preseason
MatchesRankingsPrompts
GitHub
Preseason
MatchesRankingsPromptsMethodologyContact

© 2026 Preseason. All rights reserved.

PrivacyTerms
@betocmn
AI / LLM Integration
Methodology

Anthropic vs Intercom

AnthropicANAnthropicvsINIntercom
AnthropicIntercom
49%
51%

Leading: Intercom (50.8%)

Statistics

MetricValue
Anthropic wins96
Intercom wins99
Abstains (no tool)19
Other tool chosen2387
Decisive cases195
Anthropic win rate (unweighted)49.2%
95% CI42.3% - 56.2%
Anthropic win rate (weighted)49.2%

Comments

Anthropic

No comments yet

Verified critics can leave comments here.

Intercom

No comments yet

Verified critics can leave comments here.

Per-model breakdown

ModelTierAnthropicIntercomNoneOtherA rate
Claude Haiku 4.5Small60407694%
MiniMax M2.7Frontier18809469%
Mistral Small 4Mid101428342%
Llama 4 ScoutSmall02021140%
Claude Sonnet 4.6Frontier01301280%
DeepSeek V3.2Mid01301180%
GPT 5.4Frontier0901230%
GPT 5.4 MiniMid0711330%
Llama 4 MaverickFrontier0531280%
Kimi K2.7 CodeFrontier2007100%
DeepSeek V4 FlashMid110750%
Kimi K2.5Frontier11111550%
MiMo V2 ProFrontier0201280%
Gemini 3.5 FlashSmall1007100%
GLM 5 TurboFrontier102128100%
GPT 5.5Frontier1006100%
MiniMax M3Frontier1008100%
DeepSeek R1 0528Frontier0121350%
Gemini 2.5 ProFrontier0121380%
Claude Opus 4.6Frontier000132n/a
Claude Opus 4.8Frontier0008n/a
DeepSeek V4 ProFrontier0018n/a
Devstral 2 2512Mid002135n/a
Gemini 2.5 FlashSmall000132n/a
GLM 5.2Frontier0009n/a
GPT 5.3 CodexFrontier000141n/a
MiMo V2.5 ProFrontier0009n/a
Qwen3 Coder NextMid001137n/a

Per-prompt breakdown

PromptTierAnthropicIntercomNoneOtherA rate
ai-support-agent-platformBeginner109913089%
ai-revenue-ops-copilotIntermediate2501406100%
ai-support-agent-platformIntermediate2400410100%
ai-revenue-ops-copilotBeginner1800389100%
ai-support-agent-platformAdvanced901421100%
ai-revenue-ops-copilotAdvanced403415100%
ai-agent-applicationIntermediate20510100%
ai-agent-applicationAdvanced20315100%
ai-agent-applicationBeginner20513100%