Claude 3.5 Haiku — Retired model
Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic...
Technical specifications
Independent benchmarks
Scores below come from Artificial Analysis, an independent third party. BazaarLink does not participate in the testing.
Intelligence 12
Coding 16
Math
MMLU 63
GPQA 41
This modelCategory leader
Coding ability
#157out of 198 models
LiveCodeBench / SciCode and similar
Overall intelligence
#329out of 573 models
Aggregated across academic benchmarks
Time to first token
🥇
#1out of 586 models
AA 全球 p50：0.00 秒
Intelligence
12
Mid-tierThis model12
Category leader61
Median15
Coding
16
Mid-tierThis model16
Category leader78
Median37
MMLU Pro
63%
—This model63%
Category leader90%
Median75%
GPQA
41%
—This model41%
Category leader94%
Median69%
LiveCodeBench
31%
—This model31%
Category leader42%
Median42%
HLE
4%
—This model4%
Category leader53%
Median7%
SciCode
27%
—This model27%
Category leader60%
Median33%
IFBench
43%
—This model43%
Category leader83%
Median44%
τ²-Bench Telecom
25%
—This model25%
Category leader99%
Median46%
AA-LCR
23%
—This model23%
Category leader76%
Median40%
Terminal-Bench Hard
2%
—This model2%
Category leader66%
Median14%
Top 5 — CodingCoding Index leaderboard
1GPT-5.6 Sol (xhigh)
openai/gpt-5-6-sol-xhigh78$5 / $304GPT-5.6 Sol (high)
openai/gpt-5-6-sol-high77$5 / $305Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
anthropic/claude-opus-5-xhigh77$5 / $25AASource: Artificial Analysis · Independent third-party evaluation; not influenced by BazaarLinkView full evaluation on AA →
Frequently Asked Questions
Can I still use the retired Claude 3.5 Haiku model?
No. Claude 3.5 Haiku has been retired and is retained here only as a historical reference. See the active alternatives linked on this page.
Relay integrity checks
No integrity-check data is available for this model yet.
BazaarLink Probe verifies endpoints that claim to serve this model and flags behavior that differs from the reference baseline.
View the full integrity report →Related models and links
More from this provider: Anthropic