DeepSeek / arena-v1

DeepSeek V4 Flash benchmark.

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

Evidence levelCited snapshot

Last update2026-08-07

Categories5

Combined quality

79.6

Arena score

Pending

Median latency

Pending

Valid votes

0

Task analysis

Performance by task.

Category	Quality	Arena	External	Evidence
coding	79.0	Pending	79.0	Cited snapshot
general	80.9	Pending	80.9	Cited snapshot
overall	79.6	Pending	79.6	Cited snapshot
reasoning	76.2	Pending	76.2	Cited snapshot
writing	81.1	Pending	81.1	Cited snapshot

Provenance

External evidence.

LMArena Text Leaderboard

2026-08-03 text_style_control 0fdff69b4fd7

overallRank #791435.6 raw79.6 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 2026-08-03 / 48,667 source votes / retrieved 2026-08-07 / 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: 4e52c8e709c90a4cad8498d9db5aad11709b04e0. LMArena is not affiliated with RouterPlex.

LMArena Text Leaderboard

2026-08-03 text_style_control 0fdff69b4fd7

codingRank #801483.5 raw79.0 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 2026-08-03 / 14,270 source votes / retrieved 2026-08-07 / 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: 4e52c8e709c90a4cad8498d9db5aad11709b04e0. LMArena is not affiliated with RouterPlex.

LMArena Text Leaderboard

2026-08-03 text_style_control 0fdff69b4fd7

reasoningRank #891426.6 raw76.2 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 2026-08-03 / 2,496 source votes / retrieved 2026-08-07 / 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: 4e52c8e709c90a4cad8498d9db5aad11709b04e0. LMArena is not affiliated with RouterPlex.

LMArena Text Leaderboard

2026-08-03 text_style_control 0fdff69b4fd7

writingRank #731407.4 raw81.1 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 2026-08-03 / 7,898 source votes / retrieved 2026-08-07 / 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: 4e52c8e709c90a4cad8498d9db5aad11709b04e0. LMArena is not affiliated with RouterPlex.

LMArena Text Leaderboard

2026-08-03 text_style_control 0fdff69b4fd7

generalRank #741428.3 raw80.9 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 2026-08-03 / 16,488 source votes / retrieved 2026-08-07 / 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: 4e52c8e709c90a4cad8498d9db5aad11709b04e0. LMArena is not affiliated with RouterPlex.

Your workload is the final benchmark

Test DeepSeek V4 Flash yourself.

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

Open playground Compare in Arena

DeepSeek V4 Flash Benchmarks · RouterPlex