Anthropic · arena-v1

Claude Opus 4.8 benchmark

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

Combined quality

94.4

Arena score

Insufficient data

Median latency

Insufficient data

Votes

0

Performance by task.

CategoryQualityArenaExternalEvidence
coding97.6Insufficient data97.6External snapshot
general96.3Insufficient data96.3External snapshot
overall94.4Insufficient data94.4External snapshot
reasoning94.3Insufficient data94.3External snapshot
writing95.5Insufficient data95.5External snapshot

External sources.

LMArena Text Leaderboard · 2026-07-21 text_style_controloverall: rank #22 · 1473.4 raw · 94.4 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 2026-07-21 · 31,619 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 #10 · 1529.6 raw · 97.6 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 · 8,875 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 #22 · 1476.1 raw · 94.3 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 · 1,532 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 #18 · 1458.6 raw · 95.5 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 · 5,515 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 #15 · 1477.6 raw · 96.3 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 · 10,733 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.

Compare Claude Opus 4.8.

Claude Opus 4.8 vs GPT-5.5

Test Claude Opus 4.8 yourself.

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

Open in playgroundCompare in Arena
Claude Opus 4.8 Benchmark, Arena Rank and Value · RouterPlex