AI ScoreboardFrontend & Coding Index← Back to rankings

MODEL PROFILE / EDITION 2026.09

Tencent Hy3

High-volume, cost-capped code and content generation where design quality is not critical

TencentRank 30Confidence CNo prior snapshot
65.6

Balanced model evidence score; rank 30. No rank delta is shown because there is no prior numeric snapshot.

Best for

High-volume, cost-capped code and content generation where design quality is not critical

Price & access

$0.14 in / $0.55 out per 1M (Artificial Analysis) - the cheapest model in this set

Evidence summary

Price, context and speed come only from Artificial Analysis; the single SWE-bench row is labelled 'Preview' and may not correspond to GA hy3; modalities and max output are undocumented on fetched pages.

Edition status

No prior snapshot. Tracked in the September 2026 baseline.

Strengths

  • Cheapest tokens in this set ($0.14/$0.55) with Apache 2.0 weights
  • 94.8 tok/s with 2.76 s TTFT - genuinely responsive
  • SWE-bench Verified 74.4% is respectable for the price tier
  • Free in Tencent's own dev products until Sep 30, 2026

Tradeoffs

  • Design Arena Website 1197 (rank 64) is the weakest visual score in this set
  • 256k context is the smallest here
  • AA Intelligence Index 33 is low
  • The only SWE-bench row is labelled 'Preview', so it may not match GA hy3

Score profile

visual 58 · code 64 · agentic 60 · debug 58 · context 62 · speed 78 · value 95

Linked evidence

Evidence source 1 ↗Evidence source 2 ↗Evidence source 3 ↗Evidence source 4 ↗Evidence source 5 ↗
Compare this model on the full scoreboard

Use the same published data, filters, and side-by-side metrics.

Open comparison view →