DeepSeek · arena-v1

DeepSeek V4 Flash benchmark

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

Combined quality

80.1

Arena score

Insufficient data

Median latency

Insufficient data

Votes

0

Performance by task.

CategoryQualityArenaExternalEvidence
coding80.1Insufficient data80.1External snapshot
general81.7Insufficient data81.7External snapshot
overall80.1Insufficient data80.1External snapshot
reasoning76.0Insufficient data76.0External snapshot
writing81.6Insufficient data81.6External snapshot

External sources.

LMArena Text Leaderboard · 2026-07-21 text_style_controloverall: rank #76 · 1435.5 raw · 80.1 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 2026-07-21 · 45,050 source votes · retrieved 2026-07-22 · LMArena leaderboard dataset, licensed CC BY 4.0. RouterPlex includes only exact case-insensitive model-ID matches. LMArena is not affiliated with RouterPlex.

LMArena Text Leaderboard · 2026-07-21 text_style_controlcoding: rank #75 · 1482.3 raw · 80.1 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 2026-07-21 · 13,172 source votes · retrieved 2026-07-22 · LMArena leaderboard dataset, licensed CC BY 4.0. RouterPlex includes only exact case-insensitive model-ID matches. LMArena is not affiliated with RouterPlex.

LMArena Text Leaderboard · 2026-07-21 text_style_controlreasoning: rank #89 · 1425.7 raw · 76.0 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 2026-07-21 · 2,313 source votes · retrieved 2026-07-22 · LMArena leaderboard dataset, licensed CC BY 4.0. RouterPlex includes only exact case-insensitive model-ID matches. LMArena is not affiliated with RouterPlex.

LMArena Text Leaderboard · 2026-07-21 text_style_controlwriting: rank #70 · 1408.2 raw · 81.6 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 2026-07-21 · 7,197 source votes · retrieved 2026-07-22 · LMArena leaderboard dataset, licensed CC BY 4.0. RouterPlex includes only exact case-insensitive model-ID matches. LMArena is not affiliated with RouterPlex.

LMArena Text Leaderboard · 2026-07-21 text_style_controlgeneral: rank #70 · 1428.1 raw · 81.7 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 2026-07-21 · 15,148 source votes · retrieved 2026-07-22 · LMArena leaderboard dataset, licensed CC BY 4.0. RouterPlex includes only exact case-insensitive model-ID matches. LMArena is not affiliated with RouterPlex.

Test DeepSeek V4 Flash yourself.

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

Open in playgroundCompare in Arena
DeepSeek V4 Flash Benchmark, Arena Rank and Value · RouterPlex