Tencent Hunyuan / arena-v1

Hy3 benchmark.

Blind preference, cited external scores, and evaluation economics. Every result keeps its sample count and source date attached.

Evidence levelCited snapshot

Last update2026-09-10

Categories5

Combined quality

85.4

Arena score

Pending

Median latency

Pending

Valid votes

0

Task analysis

Performance by task.

Category	Quality	Arena	External	Evidence
coding	85.0	Pending	85.0	Cited snapshot
general	85.2	Pending	85.2	Cited snapshot
overall	85.4	Pending	85.4	Cited snapshot
reasoning	91.1	Pending	91.1	Cited snapshot
writing	82.8	Pending	82.8	Cited snapshot

Provenance

External evidence.

LMArena Text Leaderboard

2026-09-02 text_style_control b005f0dd4ad8

overallRank #591455.4 raw85.4 percentile

Bradley-Terry ratings from LMArena's style-controlled text leaderboard. RouterPlex preserves the raw rating, source rank, confidence interval, vote count, and publish date. The displayed external score is the source-rank percentile within each source category.

Published 2026-09-02 / 6,958 source votes / retrieved 2026-09-10 / LMArena leaderboard dataset, licensed CC BY 4.0. RouterPlex includes only exact case-insensitive model-ID matches. Official leaderboard: https://arena.ai/leaderboard. Dataset: https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset. Dataset commit: 96b7dbb8ef2421bf3b79d08b87ebaacc56961618. LMArena is not affiliated with RouterPlex.

LMArena Text Leaderboard

2026-09-02 text_style_control b005f0dd4ad8

codingRank #601502.4 raw85.0 percentile

Bradley-Terry ratings from LMArena's style-controlled text leaderboard. RouterPlex preserves the raw rating, source rank, confidence interval, vote count, and publish date. The displayed external score is the source-rank percentile within each source category.

Published 2026-09-02 / 1,947 source votes / retrieved 2026-09-10 / LMArena leaderboard dataset, licensed CC BY 4.0. RouterPlex includes only exact case-insensitive model-ID matches. Official leaderboard: https://arena.ai/leaderboard. Dataset: https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset. Dataset commit: 96b7dbb8ef2421bf3b79d08b87ebaacc56961618. LMArena is not affiliated with RouterPlex.

LMArena Text Leaderboard

2026-09-02 text_style_control b005f0dd4ad8

reasoningRank #351475.2 raw91.1 percentile

Bradley-Terry ratings from LMArena's style-controlled text leaderboard. RouterPlex preserves the raw rating, source rank, confidence interval, vote count, and publish date. The displayed external score is the source-rank percentile within each source category.

Published 2026-09-02 / 359 source votes / retrieved 2026-09-10 / LMArena leaderboard dataset, licensed CC BY 4.0. RouterPlex includes only exact case-insensitive model-ID matches. Official leaderboard: https://arena.ai/leaderboard. Dataset: https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset. Dataset commit: 96b7dbb8ef2421bf3b79d08b87ebaacc56961618. LMArena is not affiliated with RouterPlex.

LMArena Text Leaderboard

2026-09-02 text_style_control b005f0dd4ad8

writingRank #691422.9 raw82.8 percentile

Bradley-Terry ratings from LMArena's style-controlled text leaderboard. RouterPlex preserves the raw rating, source rank, confidence interval, vote count, and publish date. The displayed external score is the source-rank percentile within each source category.

Published 2026-09-02 / 1,325 source votes / retrieved 2026-09-10 / LMArena leaderboard dataset, licensed CC BY 4.0. RouterPlex includes only exact case-insensitive model-ID matches. Official leaderboard: https://arena.ai/leaderboard. Dataset: https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset. Dataset commit: 96b7dbb8ef2421bf3b79d08b87ebaacc56961618. LMArena is not affiliated with RouterPlex.

LMArena Text Leaderboard

2026-09-02 text_style_control b005f0dd4ad8

generalRank #601445.4 raw85.2 percentile

Bradley-Terry ratings from LMArena's style-controlled text leaderboard. RouterPlex preserves the raw rating, source rank, confidence interval, vote count, and publish date. The displayed external score is the source-rank percentile within each source category.

Published 2026-09-02 / 2,433 source votes / retrieved 2026-09-10 / LMArena leaderboard dataset, licensed CC BY 4.0. RouterPlex includes only exact case-insensitive model-ID matches. Official leaderboard: https://arena.ai/leaderboard. Dataset: https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset. Dataset commit: 96b7dbb8ef2421bf3b79d08b87ebaacc56961618. LMArena is not affiliated with RouterPlex.

Your workload is the final benchmark

Test Hy3 yourself.

Use it directly, or put it into a blind head-to-head comparison.

Open playground Compare in Arena

Hy3 Benchmarks · RouterPlex