Model detail
Hy3 Preview(Free Model)
tencent/hy3-preview:free
T6.3Overall scoreOverall rank 5/6Benchmark runs 2
Score6.3
Pass rate7.1
Tests1/14
Runs2
Avg latency14.80s
TTFT (Ø)53500 ms
Decode (Ø)46.5 tok/s
Leading categoriesCoding Ui
Est. cost$0.00
Tokens (Σ)1.2k pr / 10.2k comp
Score over runs
Overall score % from merged run_models rows (chronological). Only runs that include this model appear as points.
Category performance
Score % (left axis) vs mean latency per category (seconds, right). With typical 0/1 scorers, pass rate tracks score; both are shown in the tooltip and breakdown table.
Tests per category
Number of merged result rows from local run reports (coverage in your dataset, not total fixtures).
Difficulty levels
Speed profile by category
Normalized 0–100 within this model: TTFT (shorter → higher spoke) and decode tok/s (higher → higher spoke). Values come from streamed BLXBench runs merged into overall_ranking.json.
CategoryRankPassScoreLatencytok/sCost
Coding Ui2/61/244.079.62s171.3$0.00
Debugging6/60/20.03.34s29.9$0.00
Hallucination5/60/20.02.99s6.7$0.00
Reasoning6/60/20.03.68s21.9$0.00
Refactoring4/60/20.06.52s41.8$0.00
Security6/60/20.03.76s32.0$0.00
Speed6/60/20.03.68s22.1$0.00
Cost by category
Sum of estimated API costs (USD) per benchmark domain for this model.