b.buildnscale
ToolsAI benchmarksBuild logRoadmap
Open workspace
buildnscale

A little less friction.
A little more shipped.

Built in the open

Your toolkit

Daily Focus PlannerPomodoro + Task LogMarkdown NotesJSON ToolkitDowntime DetectorFreelancer Rate CalculatorHabit Streak TrackerWeekly Review Dashboard

Around here

AI benchmarksCompare AI modelsBenchmark methodologyBuild logRoadmapChangelogWrite for usBack up your workspacePrivacyTermsSuggest a tool ↗
© 2026 BuildnScale · Muhammad YousafFree to use. Built for your next small win.
BUILDNSCALE / AI BENCHMARKSEvidence for your next build
OverviewCodingAgentsPrice & performanceModelsCompareMethodologyUpdatesArchive

Meet the evaluated models.

Exact labels from the selected evaluator. Historical model labels are preserved; availability, licenses, and current API aliases should be checked with the publisher.

Archive (2024)Latest imported results

Arena published dataset · source published (oldest included board) 22 Oct 2026

Latest published overall boards for text, web development, and agents. Each rating has its own scale and publication date. Results are imported, not evaluated by BuildnScale. Update check overdue: no successful source check in the last eight hours. Displaying the last validated snapshot.

Retrieved 26 Oct 2026 · Last successful check 2026-10-26 22:34:24 UTC · View exact source ↗ · CC BY 4.0

Source: Arena / lmarena-ai leaderboard dataset, CC BY 4.0. Filtered to the latest overall boards and normalized by BuildnScale; evaluations were not rerun. No endorsement implied.

Loading catalog…

Published evidence. Clear sources. No sponsored rank placement.

How to read these results →

461 models · Arena Text (style controlled) · Higher is better

Arena text preference rating (overall, style controlled). Not a percentage or coding pass rate. Ranks apply only to this source snapshot and selected metric. Arena ranks are preserved from the source; other ranks use exact scores. Small differences do not establish statistical superiority.

Arena Text (style controlled) results from arena. Select models to compare.
CompareRankModel / evaluated labelArena Text (style controlled)Source
#1Gemini 4 Argon (High)google1517.2

Source CI: 1510.6 to 1523.8

10,083 votes

Published 2026-10-22

Evidence
#2Claude Opus 5.5 (High)anthropic1508.7

Source CI: 1501.9 to 1515.5

10,322 votes

Published 2026-10-22

Evidence
#3Muse Wonder (Max)meta1508.7

Source CI: 1500.6 to 1516.8

6,001 votes

Published 2026-10-22

Evidence
#4Claude Fable 5 (High)anthropic1503.3

Source CI: 1499.1 to 1507.5

44,253 votes

Published 2026-10-22

Evidence
#5Claude Fable 5.1 (Max)anthropic1503.2

Source CI: 1497.3 to 1509.1

16,343 votes

Published 2026-10-22

Evidence
#6Claude Opus 4.6 (High)anthropic1502.9

Source CI: 1499.6 to 1506.2

83,454 votes

Published 2026-10-22

Evidence
#7Claude Opus 4.7 (High)anthropic1501.1

Source CI: 1497.3 to 1504.8

65,140 votes

Published 2026-10-22

Evidence
#8Claude Opus 4.6anthropic1496.7

Source CI: 1493.4 to 1499.9

88,206 votes

Published 2026-10-22

Evidence
#9Gemini 3.8 Flash (High)google1495.7

Source CI: 1491.2 to 1500.2

43,997 votes

Published 2026-10-22

Evidence
#10Muse Spark 1.3 (Max)meta1495.6

Source CI: 1490.2 to 1500.9

20,506 votes

Published 2026-10-22

Evidence
#11Claude Opus 4.7anthropic1493.7

Source CI: 1489.9 to 1497.4

66,183 votes

Published 2026-10-22

Evidence
#12Muse Spark 1.2 (xHigh)meta1491.4

Source CI: 1484.8 to 1497.9

10,470 votes

Published 2026-10-22

Evidence
#13Claude Opus 5 (Max)anthropic1490.9

Source CI: 1486.1 to 1495.6

34,526 votes

Published 2026-10-22

Evidence
#14Claude Opus 5 (High)anthropic1490.7

Source CI: 1487.1 to 1494.3

71,020 votes

Published 2026-10-22

Evidence
#15Muse Spark 1.1meta1489.9

Source CI: 1485.7 to 1494.0

46,121 votes

Published 2026-10-22

Evidence
#16Gemini 3.7 Flash (High)google1489.8

Source CI: 1485.1 to 1494.6

30,501 votes

Published 2026-10-22

Evidence
#17Muse Sparkmeta1489.2

Source CI: 1483.5 to 1495.0

14,147 votes

Published 2026-10-22

Evidence
#18Kimi K3 (Max)moonshot1487.4

Source CI: 1482.9 to 1491.9

35,379 votes

Published 2026-10-22

Evidence
#19Gemini 3.1 Pro Previewgoogle1487.0

Source CI: 1484.1 to 1490.0

130,819 votes

Published 2026-10-22

Evidence
#20Gemini 3 Progoogle1485.5

Source CI: 1481.7 to 1489.3

42,054 votes

Published 2026-10-22

Evidence
#21GPT-5.6 Sol (xHigh)openai1485.1

Source CI: 1480.9 to 1489.4

42,713 votes

Published 2026-10-22

Evidence
#22Gemini 3.6 Flash (High)google1483.0

Source CI: 1478.6 to 1487.5

36,102 votes

Published 2026-10-22

Evidence
#23Qwen3.8-Maxalibaba1482.9

Source CI: 1478.1 to 1487.7

30,500 votes

Published 2026-10-22

Evidence
#24GPT-5.5 (High)openai1481.6

Source CI: 1477.9 to 1485.4

69,375 votes

Published 2026-10-22

Evidence
#25Claude Opus 4.8 (High)anthropic1481.5

Source CI: 1477.6 to 1485.3

64,096 votes

Published 2026-10-22

Evidence

#1

Gemini 4 Argon (High)
1517.2Arena Text (style controlled)

Source CI: 1510.6 to 1523.8

10,083 votes

Published 2026-10-22

googleEvidence

#2

Claude Opus 5.5 (High)
1508.7Arena Text (style controlled)

Source CI: 1501.9 to 1515.5

10,322 votes

Published 2026-10-22

anthropicEvidence

#3

Muse Wonder (Max)
1508.7Arena Text (style controlled)

Source CI: 1500.6 to 1516.8

6,001 votes

Published 2026-10-22

metaEvidence

#4

Claude Fable 5 (High)
1503.3Arena Text (style controlled)

Source CI: 1499.1 to 1507.5

44,253 votes

Published 2026-10-22

anthropicEvidence

#5

Claude Fable 5.1 (Max)
1503.2Arena Text (style controlled)

Source CI: 1497.3 to 1509.1

16,343 votes

Published 2026-10-22

anthropicEvidence

#6

Claude Opus 4.6 (High)
1502.9Arena Text (style controlled)

Source CI: 1499.6 to 1506.2

83,454 votes

Published 2026-10-22

anthropicEvidence

#7

Claude Opus 4.7 (High)
1501.1Arena Text (style controlled)

Source CI: 1497.3 to 1504.8

65,140 votes

Published 2026-10-22

anthropicEvidence

#8

Claude Opus 4.6
1496.7Arena Text (style controlled)

Source CI: 1493.4 to 1499.9

88,206 votes

Published 2026-10-22

anthropicEvidence

#9

Gemini 3.8 Flash (High)
1495.7Arena Text (style controlled)

Source CI: 1491.2 to 1500.2

43,997 votes

Published 2026-10-22

googleEvidence

#10

Muse Spark 1.3 (Max)
1495.6Arena Text (style controlled)

Source CI: 1490.2 to 1500.9

20,506 votes

Published 2026-10-22

metaEvidence

#11

Claude Opus 4.7
1493.7Arena Text (style controlled)

Source CI: 1489.9 to 1497.4

66,183 votes

Published 2026-10-22

anthropicEvidence

#12

Muse Spark 1.2 (xHigh)
1491.4Arena Text (style controlled)

Source CI: 1484.8 to 1497.9

10,470 votes

Published 2026-10-22

metaEvidence

#13

Claude Opus 5 (Max)
1490.9Arena Text (style controlled)

Source CI: 1486.1 to 1495.6

34,526 votes

Published 2026-10-22

anthropicEvidence

#14

Claude Opus 5 (High)
1490.7Arena Text (style controlled)

Source CI: 1487.1 to 1494.3

71,020 votes

Published 2026-10-22

anthropicEvidence

#15

Muse Spark 1.1
1489.9Arena Text (style controlled)

Source CI: 1485.7 to 1494.0

46,121 votes

Published 2026-10-22

metaEvidence

#16

Gemini 3.7 Flash (High)
1489.8Arena Text (style controlled)

Source CI: 1485.1 to 1494.6

30,501 votes

Published 2026-10-22

googleEvidence

#17

Muse Spark
1489.2Arena Text (style controlled)

Source CI: 1483.5 to 1495.0

14,147 votes

Published 2026-10-22

metaEvidence

#18

Kimi K3 (Max)
1487.4Arena Text (style controlled)

Source CI: 1482.9 to 1491.9

35,379 votes

Published 2026-10-22

moonshotEvidence

#19

Gemini 3.1 Pro Preview
1487.0Arena Text (style controlled)

Source CI: 1484.1 to 1490.0

130,819 votes

Published 2026-10-22

googleEvidence

#20

Gemini 3 Pro
1485.5Arena Text (style controlled)

Source CI: 1481.7 to 1489.3

42,054 votes

Published 2026-10-22

googleEvidence

#21

GPT-5.6 Sol (xHigh)
1485.1Arena Text (style controlled)

Source CI: 1480.9 to 1489.4

42,713 votes

Published 2026-10-22

openaiEvidence

#22

Gemini 3.6 Flash (High)
1483.0Arena Text (style controlled)

Source CI: 1478.6 to 1487.5

36,102 votes

Published 2026-10-22

googleEvidence

#23

Qwen3.8-Max
1482.9Arena Text (style controlled)

Source CI: 1478.1 to 1487.7

30,500 votes

Published 2026-10-22

alibabaEvidence

#24

GPT-5.5 (High)
1481.6Arena Text (style controlled)

Source CI: 1477.9 to 1485.4

69,375 votes

Published 2026-10-22

openaiEvidence

#25

Claude Opus 4.8 (High)
1481.5Arena Text (style controlled)

Source CI: 1477.6 to 1485.3

64,096 votes

Published 2026-10-22

anthropicEvidence
Page 1 of 19

Source: Arena / lmarena-ai leaderboard dataset, CC BY 4.0. Filtered to the latest overall boards and normalized by BuildnScale; evaluations were not rerun. No endorsement implied.