Expired50% confidenceFactTime unknown
Claude Haiku 4.5 failed all 5 programming task tests
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Claude Haiku 4.5 Real-World Test: Failed All 5 Programming Tasks
bilibilikarminski-牙医
Related Claims
UnverifiedThe independent tester ran tests on Claude 4.5 Haiku more than five times repeatedly, and the results consistently showed poor performance.80% similarUnverifiedClaude Haiku 4.5 failed to achieve a chain explosion effect in all 6 tests of the firecracker chain explosion test77% similarUnverifiedClaude Haiku 4.5 surpasses the larger Sonnet 4.5 on certain computer use task benchmarks.70% similarUnverifiedClaude Haiku 4.5 has a lower false refusal rate than Sonnet 4.5 and Opus 4.1, making it one of the safest models Anthropic has released to date.66% similarUnverifiedIn an independent tester's overall rankings, Claude 4.5 Haiku placed 34th and 37th respectively, making it the lowest-scoring next-generation model among mainstream AI labs.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/54458API
curl https://kongchang.com/api/v1/knowledge/claims/54458MCP
get_claim(id=54458)