Hy3 Preview — Retired model
This model has reached end of life and is no longer available through BazaarLink. Historical specifications and independent benchmarks remain below.
Technical specifications
Independent benchmarks
Scores below come from Artificial Analysis, an independent third party. BazaarLink does not participate in the testing.
Intelligence 34
Coding
Math
MMLU
GPQA 87
This modelCategory leader
Overall intelligence
#112out of 573 models
Aggregated across academic benchmarks
Time to first token
#526out of 586 models
AA 全球 p50：1.77 秒
Intelligence
34
Top 20%This model34
Category leader61
Median15
GPQA
87%
—This model87%
Category leader94%
Median69%
HLE
26%
—This model26%
Category leader53%
Median7%
SciCode
41%
—This model41%
Category leader60%
Median33%
IFBench
63%
—This model63%
Category leader83%
Median44%
τ²-Bench Telecom
93%
—This model93%
Category leader99%
Median46%
AA-LCR
55%
—This model55%
Category leader76%
Median40%
Terminal-Bench Hard
34%
—This model34%
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 Hy3 Preview model?
No. Hy3 Preview has been retired and is retained here only as a historical reference.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
Related models and links