Expired65% confidenceFactTime unknown

GPT-5 Mini far outperformed Claude 4.5 Haiku in comparable tests.

1

Sources

65%

Confidence

Medium-term (~90 days)

Relevance

6/1/2026

First Seen

Valid until: 8/30/2026(expired)

Sources

Claude 4.5 Haiku Real-World Testing Disaster: Coding Capabilities Collapse Across the Board, Crushed by Competitors on Value

bilibili烟神殿殿主

Related Entities

GPT-5 Minimodel Claude 4.5 Haikumodel OpenAIcompany

Related Claims

UnverifiedClaude 4.5 Haiku can almost match GPT-5 on intermediate-level programming tasks83% similar UnverifiedClaude Haiku 4.5 still holds a clear pricing advantage over peer-level models such as GPT-4o mini.82% similar UnverifiedThe article claims that Claude Haiku 4.5 outperformed GPT-5 and Gemini 2.5 Pro on several core benchmarks.81% similar Partially VerifiedThis evaluation conducted a horizontal comparison of five models: Claude Opus 4.8, GPT 5.5, MiniMax M3, Mimo 2.5 Pro, and DeepSeek V4 Pro.79% similar UnverifiedThe GPT-5.6 SOUL version outperforms the benchmark model Fable 5 on multiple tests and is more competitively priced.79% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/24357

API

curl https://kongchang.com/api/v1/knowledge/claims/24357

MCP

get_claim(id=24357)