AI Index / AI coding assistants / History

AI coding assistants — AI Recommendation History

What AI assistants recommended for ai coding assistants, date by date. Every ranking we publish is frozen the day it publishes, so this is a record of what was said — not a re-computation of what today's data would say about the past.

Record: 26 dated snapshots · Aug 14, 2026 – Sep 8, 2026

Answer archive Methodology Data studies JSON

What changed

Computed by comparing each dated snapshot with the one before it. Share moves smaller than 1pp are treated as noise and left out — the same threshold that suppresses trend arrows on the ranking.

Sep 8, 2026vs Sep 7, 2026

▼JetBrains -3.3pp (29.7% → 26.4%)
▼GitHub Copilot -2.6pp (73.4% → 70.8%)
▼VS Code -2.6pp (60.9% → 58.3%)
▼Aider -2.1pp (31.3% → 29.2%)
▲Cursor +2pp (68.8% → 70.8%)
▼Continue -1.4pp (37.5% → 36.1%)

Sep 7, 2026vs Sep 6, 2026

▲ INTabby entered the top 10 (#11 → #10)
▼ OUTGemini Code Assist left the top 10 (#10 → #13)
▼Gemini Code Assist moved #10 → #13
▲Continue moved #6 → #5
▼Tabnine moved #5 → #6
▲Aider moved #9 → #8
▼JetBrains moved #8 → #9
▲Tabby moved #11 → #10
▲VS Code +10.9pp (50% → 60.9%)
▲Aider +9.4pp (21.9% → 31.3%)
▲Claude Code +7.8pp (37.5% → 45.3%)
▲Codeium +4.7pp (28.1% → 32.8%)
▲JetBrains +4.7pp (25% → 29.7%)
▲GitHub Copilot +4.6pp (68.8% → 73.4%)
▲Continue +3.1pp (34.4% → 37.5%)
▼Tabnine -3.1pp (37.5% → 34.4%)
▲Tabby +3.1pp (18.8% → 21.9%)
▼Gemini Code Assist -1.6pp (21.9% → 20.3%)

Sep 6, 2026vs Sep 5, 2026

Methodology change: extraction rules 5-7 → 7 between these dates. Differences below may reflect the rule change rather than a change in what AI recommends — see the methodology changelog.

▲ INAider entered the top 10 (#11 → #9)
▼ OUTTabby left the top 10 (#10 → #11)
▲Aider moved #11 → #9
▲GitHub Copilot moved #2 → #1
▼Cursor moved #1 → #2
▲Tabnine moved #6 → #5
▼Continue moved #5 → #6
▲Codeium moved #8 → #7
▼JetBrains moved #7 → #8
▼Gemini Code Assist moved #9 → #10
▼Tabby moved #10 → #11
▲Tabnine +7.5pp (30% → 37.5%)
▲Codeium +5.6pp (22.5% → 28.1%)
▼Cursor -3.7pp (72.5% → 68.8%)
▼VS Code -2.5pp (52.5% → 50%)
▼Claude Code -2.5pp (40% → 37.5%)
▼JetBrains -2.5pp (27.5% → 25%)
▲Continue +1.9pp (32.5% → 34.4%)
▲Aider +1.9pp (20% → 21.9%)
▼GitHub Copilot -1.2pp (70% → 68.8%)
▼Tabby -1.2pp (20% → 18.8%)

Sep 5, 2026vs Sep 4, 2026

Methodology change: extraction rules 4-7 → 5-7 between these dates. Differences below may reflect the rule change rather than a change in what AI recommends — see the methodology changelog.

▲ INGemini Code Assist entered the top 10 (#12 → #9)
▲ INTabby entered the top 10 (#11 → #10)
▼ OUTAider left the top 10 (#9 → #11)
▼ OUTWindsurf left the top 10 (#10 → #14)
▼Windsurf moved #10 → #14
▲Gemini Code Assist moved #12 → #9
▼Aider moved #9 → #11
▲Tabby moved #11 → #10
▼Windsurf -5.8pp (20.8% → 15%)
▲Gemini Code Assist +3.7pp (18.8% → 22.5%)
▲JetBrains +2.5pp (25% → 27.5%)
▼VS Code -1.7pp (54.2% → 52.5%)
▼Claude Code -1.7pp (41.7% → 40%)
▼Tabnine -1.3pp (31.3% → 30%)
▲Tabby +1.2pp (18.8% → 20%)

Sep 4, 2026vs Sep 3, 2026

▲Cursor moved #2 → #1
▼GitHub Copilot moved #1 → #2
▲Continue moved #6 → #5
▼Tabnine moved #5 → #6
▲JetBrains moved #8 → #7
▼Codeium moved #7 → #8
▼Codeium -8.4pp (31.3% → 22.9%)
▼Tabnine -7.8pp (39.1% → 31.3%)
▼VS Code -3.6pp (57.8% → 54.2%)
▼JetBrains -3.1pp (28.1% → 25%)
▼GitHub Copilot -2.6pp (73.4% → 70.8%)

Sep 3, 2026vs Sep 2, 2026

No change above the noise floor.

Sep 2, 2026vs Sep 1, 2026

No change above the noise floor.

Sep 1, 2026vs Aug 31, 2026

No change above the noise floor.

Aug 31, 2026vs Aug 30, 2026

No change above the noise floor.

Aug 30, 2026vs Aug 29, 2026

▲ INWindsurf entered the top 10 (#13 → #10)
▼ OUTGemini Code Assist left the top 10 (#10 → #11)
▲Windsurf moved #13 → #10
▲Continue moved #7 → #6
▼Codeium moved #6 → #7
▼Gemini Code Assist moved #10 → #11
▼VS Code -4.7pp (62.5% → 57.8%)
▲Windsurf +4.2pp (16.1% → 20.3%)
▼Codeium -2.6pp (33.9% → 31.3%)
▲Aider +2.4pp (17.9% → 20.3%)
▼JetBrains -2.3pp (30.4% → 28.1%)
▲Cursor +2pp (71.4% → 73.4%)
▲Claude Code +1.1pp (41.1% → 42.2%)

Aug 29, 2026vs Aug 28, 2026

Methodology change: extraction rules 4-5 → 4-7 between these dates. Differences below may reflect the rule change rather than a change in what AI recommends — see the methodology changelog.

▲ INAider entered the top 10 (#11 → #9)
▲ INGemini Code Assist entered the top 10 (#16 → #10)
▼ OUTWindsurf left the top 10 (#9 → #13)
▼ OUTGit left the top 10 (#10 → #17)
▼Git moved #10 → #17
▲Gemini Code Assist moved #16 → #10
▼Windsurf moved #9 → #13
▲Aider moved #11 → #9
▲Continue moved #8 → #7
▼JetBrains moved #7 → #8
▼Cursor -6.7pp (78.1% → 71.4%)
▼Claude Code -5.8pp (46.9% → 41.1%)
▼Windsurf -5.8pp (21.9% → 16.1%)
▼GitHub Copilot -4.9pp (78.1% → 73.2%)
▼Git -4.5pp (18.8% → 14.3%)
▼VS Code -3.1pp (65.6% → 62.5%)
▲Gemini Code Assist +2.3pp (15.6% → 17.9%)
▼Tabnine -1.3pp (40.6% → 39.3%)

Aug 28, 2026vs Aug 27, 2026

No change above the noise floor.

Aug 27, 2026vs Aug 26, 2026

▲ INGit entered the top 10 (#15 → #10)
▼ OUTAWS left the top 10 (#10 → #21)
▼AWS moved #10 → #21
▲Git moved #15 → #10
▲Claude Code moved #6 → #4
▼JetBrains moved #5 → #7
▼Tabnine moved #4 → #5
▲Codeium moved #7 → #6
▼JetBrains -10.4pp (41.7% → 31.3%)
▼AWS -8.3pp (20.8% → 12.5%)
▼VS Code -5.2pp (70.8% → 65.6%)
▲Claude Code +5.2pp (41.7% → 46.9%)
▼Tabnine -5.2pp (45.8% → 40.6%)
▼Codeium -5.2pp (39.6% → 34.4%)
▲Git +2.1pp (16.7% → 18.8%)
▼GitHub Copilot -1.1pp (79.2% → 78.1%)
▼Cursor -1.1pp (79.2% → 78.1%)
▲Windsurf +1.1pp (20.8% → 21.9%)

Aug 26, 2026vs Aug 25, 2026

No change above the noise floor.

Aug 25, 2026vs Aug 24, 2026

No change above the noise floor.

Aug 24, 2026vs Aug 23, 2026

No change above the noise floor.

Aug 23, 2026vs Aug 22, 2026

▲ INAWS entered the top 10 (#19 → #10)
▼ OUTCody left the top 10 (#10 → #11)
▲AWS moved #19 → #10
▲Claude Code moved #7 → #6
▼Codeium moved #6 → #7
▼Cody moved #10 → #11
▼Tabnine -7.3pp (53.1% → 45.8%)
▲Claude Code +5.8pp (35.9% → 41.7%)
▲AWS +5.2pp (15.6% → 20.8%)
▼Windsurf -4.2pp (25% → 20.8%)
▼Cody -4.2pp (25% → 20.8%)
▲Cursor +2.6pp (76.6% → 79.2%)
▼Codeium -2.6pp (42.2% → 39.6%)
▼GitHub Copilot -2.1pp (81.3% → 79.2%)
▼VS Code -1.1pp (71.9% → 70.8%)

Aug 22, 2026vs Aug 21, 2026

▲JetBrains moved #6 → #5
▼Codeium moved #5 → #6
▼Windsurf -5.6pp (30.6% → 25%)
▲Cody +2.8pp (22.2% → 25%)
▲JetBrains +1.9pp (40.3% → 42.2%)
▲Tabnine +1.7pp (51.4% → 53.1%)
▼Claude Code -1.6pp (37.5% → 35.9%)
▲VS Code +1.1pp (70.8% → 71.9%)

Aug 21, 2026vs Aug 20, 2026

▲ INCody entered the top 10 (#11 → #10)
▼ OUTAider left the top 10 (#10 → #11)
▲Codeium moved #6 → #5
▼JetBrains moved #5 → #6
▲Cody moved #11 → #10
▼Aider moved #10 → #11
▼JetBrains -4.7pp (45% → 40.3%)
▼VS Code -3pp (73.8% → 70.8%)
▼Aider -3pp (23.8% → 20.8%)
▼Claude Code -2.5pp (40% → 37.5%)
▼Cursor -2.4pp (78.8% → 76.4%)
▼Windsurf -1.9pp (32.5% → 30.6%)
▲GitHub Copilot +1.8pp (78.8% → 80.6%)
▼Cody -1.6pp (23.8% → 22.2%)
▼Tabnine -1.1pp (52.5% → 51.4%)

Aug 20, 2026vs Aug 19, 2026

No change above the noise floor.

Aug 19, 2026vs Aug 18, 2026

▲Tabnine +2.5pp (50% → 52.5%)
▼JetBrains -2.1pp (47.1% → 45%)
▲Codeium +2.1pp (40.4% → 42.5%)
▼GitHub Copilot -2pp (80.8% → 78.8%)
▼VS Code -1.2pp (75% → 73.8%)

Aug 18, 2026vs Aug 17, 2026

No change above the noise floor.

Aug 17, 2026vs Aug 16, 2026

No change above the noise floor.

Aug 16, 2026vs Aug 15, 2026

No change above the noise floor.

Aug 15, 2026vs Aug 14, 2026

No change above the noise floor.

The ranking, date by date

Top 10 on each archived date, exactly as published. Cite a date and it stays true: snapshots are append-only, and a correction appends a new revision rather than overwriting the original.

Sep 8, 202672 sampled answers · window 2026-08-11 – 2026-09-08 · rules v7

#1GitHub Copilot70.8%
#2Cursor70.8%
#3VS Code58.3%
#4Claude Code44.4%
#5Continue36.1%
#6Tabnine34.7%
#7Codeium33.3%
#8Aider29.2%
#9JetBrains26.4%
#10Tabby22.2%

Sep 7, 202664 sampled answers · window 2026-08-10 – 2026-09-07 · rules v7

#1GitHub Copilot73.4%
#2Cursor68.8%
#3VS Code60.9%
#4Claude Code45.3%
#5Continue37.5%
#6Tabnine34.4%
#7Codeium32.8%
#8Aider31.3%
#9JetBrains29.7%
#10Tabby21.9%

Sep 6, 202632 sampled answers · window 2026-08-09 – 2026-09-06 · rules v7

#1GitHub Copilot68.8%
#2Cursor68.8%
#3VS Code50%
#4Claude Code37.5%
#5Tabnine37.5%
#6Continue34.4%
#7Codeium28.1%
#8JetBrains25%
#9Aider21.9%
#10Gemini Code Assist21.9%

Sep 5, 202640 sampled answers · window 2026-08-08 – 2026-09-05 · rules v5-7

#1Cursor72.5%
#2GitHub Copilot70%
#3VS Code52.5%
#4Claude Code40%
#5Continue32.5%
#6Tabnine30%
#7JetBrains27.5%
#8Codeium22.5%
#9Gemini Code Assist22.5%
#10Tabby20%

Sep 4, 202648 sampled answers · window 2026-08-07 – 2026-09-04 · rules v4-7

#1Cursor72.9%
#2GitHub Copilot70.8%
#3VS Code54.2%
#4Claude Code41.7%
#5Continue33.3%
#6Tabnine31.3%
#7JetBrains25%
#8Codeium22.9%
#9Aider20.8%
#10Windsurf20.8%

Sep 3, 202664 sampled answers · window 2026-08-06 – 2026-09-03 · rules v4-7

#1GitHub Copilot73.4%
#2Cursor73.4%
#3VS Code57.8%
#4Claude Code42.2%
#5Tabnine39.1%
#6Continue32.8%
#7Codeium31.3%
#8JetBrains28.1%
#9Aider20.3%
#10Windsurf20.3%

Sep 2, 202664 sampled answers · window 2026-08-05 – 2026-09-02 · rules v4-7

#1GitHub Copilot73.4%
#2Cursor73.4%
#3VS Code57.8%
#4Claude Code42.2%
#5Tabnine39.1%
#6Continue32.8%
#7Codeium31.3%
#8JetBrains28.1%
#9Aider20.3%
#10Windsurf20.3%

Sep 1, 202664 sampled answers · window 2026-08-04 – 2026-09-01 · rules v4-7

#1GitHub Copilot73.4%
#2Cursor73.4%
#3VS Code57.8%
#4Claude Code42.2%
#5Tabnine39.1%
#6Continue32.8%
#7Codeium31.3%
#8JetBrains28.1%
#9Aider20.3%
#10Windsurf20.3%

Aug 31, 202664 sampled answers · window 2026-08-03 – 2026-08-31 · rules v4-7

#1GitHub Copilot73.4%
#2Cursor73.4%
#3VS Code57.8%
#4Claude Code42.2%
#5Tabnine39.1%
#6Continue32.8%
#7Codeium31.3%
#8JetBrains28.1%
#9Aider20.3%
#10Windsurf20.3%

Aug 30, 202664 sampled answers · window 2026-08-02 – 2026-08-30 · rules v4-7

#1GitHub Copilot73.4%
#2Cursor73.4%
#3VS Code57.8%
#4Claude Code42.2%
#5Tabnine39.1%
#6Continue32.8%
#7Codeium31.3%
#8JetBrains28.1%
#9Aider20.3%
#10Windsurf20.3%

Aug 29, 202656 sampled answers · window 2026-08-01 – 2026-08-29 · rules v4-7

#1GitHub Copilot73.2%
#2Cursor71.4%
#3VS Code62.5%
#4Claude Code41.1%
#5Tabnine39.3%
#6Codeium33.9%
#7Continue32.1%
#8JetBrains30.4%
#9Aider17.9%
#10Gemini Code Assist17.9%

Aug 28, 202632 sampled answers · window 2026-07-31 – 2026-08-28 · rules v4-5

#1GitHub Copilot78.1%
#2Cursor78.1%
#3VS Code65.6%
#4Claude Code46.9%
#5Tabnine40.6%
#6Codeium34.4%
#7JetBrains31.3%
#8Continue31.3%
#9Windsurf21.9%
#10Git18.8%

Aug 27, 202632 sampled answers · window 2026-07-30 – 2026-08-27 · rules v4-5

#1GitHub Copilot78.1%
#2Cursor78.1%
#3VS Code65.6%
#4Claude Code46.9%
#5Tabnine40.6%
#6Codeium34.4%
#7JetBrains31.3%
#8Continue31.3%
#9Windsurf21.9%
#10Git18.8%

Aug 26, 202648 sampled answers · window 2026-07-29 – 2026-08-26 · rules v4-5

#1GitHub Copilot79.2%
#2Cursor79.2%
#3VS Code70.8%
#4Tabnine45.8%
#5JetBrains41.7%
#6Claude Code41.7%
#7Codeium39.6%
#8Continue31.3%
#9Windsurf20.8%
#10AWS20.8%

Aug 25, 202648 sampled answers · window 2026-07-28 – 2026-08-25 · rules v4-5

#1GitHub Copilot79.2%
#2Cursor79.2%
#3VS Code70.8%
#4Tabnine45.8%
#5JetBrains41.7%
#6Claude Code41.7%
#7Codeium39.6%
#8Continue31.3%
#9Windsurf20.8%
#10AWS20.8%

Aug 24, 202648 sampled answers · window 2026-07-27 – 2026-08-24 · rules v4-5

#1GitHub Copilot79.2%
#2Cursor79.2%
#3VS Code70.8%
#4Tabnine45.8%
#5JetBrains41.7%
#6Claude Code41.7%
#7Codeium39.6%
#8Continue31.3%
#9Windsurf20.8%
#10AWS20.8%

Aug 23, 202648 sampled answers · window 2026-07-26 – 2026-08-23 · rules v4-5

#1GitHub Copilot79.2%
#2Cursor79.2%
#3VS Code70.8%
#4Tabnine45.8%
#5JetBrains41.7%
#6Claude Code41.7%
#7Codeium39.6%
#8Continue31.3%
#9Windsurf20.8%
#10AWS20.8%

Aug 22, 202664 sampled answers · window 2026-07-25 – 2026-08-22 · rules v4-5

#1GitHub Copilot81.3%
#2Cursor76.6%
#3VS Code71.9%
#4Tabnine53.1%
#5JetBrains42.2%
#6Codeium42.2%
#7Claude Code35.9%
#8Continue31.3%
#9Windsurf25%
#10Cody25%

Aug 21, 202672 sampled answers · window 2026-07-24 – 2026-08-21 · rules v4-5

#1GitHub Copilot80.6%
#2Cursor76.4%
#3VS Code70.8%
#4Tabnine51.4%
#5Codeium41.7%
#6JetBrains40.3%
#7Claude Code37.5%
#8Continue31.9%
#9Windsurf30.6%
#10Cody22.2%

Aug 20, 202680 sampled answers · window 2026-07-23 – 2026-08-20 · rules v4-5

#1GitHub Copilot78.8%
#2Cursor78.8%
#3VS Code73.8%
#4Tabnine52.5%
#5JetBrains45%
#6Codeium42.5%
#7Claude Code40%
#8Continue32.5%
#9Windsurf32.5%
#10Aider23.8%

Aug 19, 202680 sampled answers · window 2026-07-22 – 2026-08-19 · rules v4-5

#1GitHub Copilot78.8%
#2Cursor78.8%
#3VS Code73.8%
#4Tabnine52.5%
#5JetBrains45%
#6Codeium42.5%
#7Claude Code40%
#8Continue32.5%
#9Windsurf32.5%
#10Aider23.8%

Aug 18, 2026104 sampled answers · window 2026-07-21 – 2026-08-18 · rules v4-5

#1GitHub Copilot80.8%
#2Cursor78.8%
#3VS Code75%
#4Tabnine50%
#5JetBrains47.1%
#6Codeium40.4%
#7Claude Code39.4%
#8Continue32.7%
#9Windsurf32.7%
#10Aider24%

Aug 17, 2026104 sampled answers · window 2026-07-20 – 2026-08-17 · rules v4-5

#1GitHub Copilot80.8%
#2Cursor78.8%
#3VS Code75%
#4Tabnine50%
#5JetBrains47.1%
#6Codeium40.4%
#7Claude Code39.4%
#8Continue32.7%
#9Windsurf32.7%
#10Aider24%

Aug 16, 2026104 sampled answers · window 2026-07-19 – 2026-08-16 · rules v4-5

#1GitHub Copilot80.8%
#2Cursor78.8%
#3VS Code75%
#4Tabnine50%
#5JetBrains47.1%
#6Codeium40.4%
#7Claude Code39.4%
#8Continue32.7%
#9Windsurf32.7%
#10Aider24%

Aug 15, 2026104 sampled answers · window 2026-07-18 – 2026-08-15 · rules v4-5

#1GitHub Copilot80.8%
#2Cursor78.8%
#3VS Code75%
#4Tabnine50%
#5JetBrains47.1%
#6Codeium40.4%
#7Claude Code39.4%
#8Continue32.7%
#9Windsurf32.7%
#10Aider24%

Aug 14, 2026104 sampled answers · window 2026-07-17 – 2026-08-14 · rules v4-5

#1GitHub Copilot80.8%
#2Cursor78.8%
#3VS Code75%
#4Tabnine50%
#5JetBrains47.1%
#6Codeium40.4%
#7Claude Code39.4%
#8Continue32.7%
#9Windsurf32.7%
#10Aider24%

Read any date directly

Every archived date is machine-readable at /api/index/ai-coding-assistants/as-of/<YYYY-MM-DD>, which returns the ranking as it stood, with the extraction version and revision it was published under. Dates before the record begins return no_record rather than a recomputation — we do not reconstruct history on demand and present it as what we said. See what the engines actually said.

[ORBATOR]