Vibeleaderboard
← Benchmark guide

Model results

Aider Polyglot Benchmark

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Official source

Evaluation groups

Open a group to see its exact protocol and scores. Different configurations remain separate.

No model rankings are available in this snapshot. Reported results remain available below.

Other reported results

These reports have no model ranking. Open a group for its evidence and the reason positions are withheld.

  • GPT-5polyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-08-25

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit 32faf82; configuration gpt-5 (low)

  • GPT-5polyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-08-25

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit 32faf82; configuration gpt-5 (mediu…

    225 polyglot tasks; two attempts; edit format diff; Aider commit 32faf82; configuration gpt-5 (medium)

  • GPT-5polyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-08-23

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit 32faf82; configuration gpt-5 (high)

  • gpt-oss-120bpolyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-08-06

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit 1af0e59; configuration gpt-oss-120b…

    225 polyglot tasks; two attempts; edit format diff; Aider commit 1af0e59; configuration gpt-oss-120b (high)

  • o3 Propolyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-06-28

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit 5318380; configuration o3-pro (high…

    225 polyglot tasks; two attempts; edit format diff; Aider commit 5318380; configuration o3-pro (high)

  • o3polyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-06-27

    Scope · 225 polyglot tasks; 224 attempted cases reported; two attempts; edit format architect; Aider commit …

    225 polyglot tasks; 224 attempted cases reported; two attempts; edit format architect; Aider commit 4f4f00f-dirty; configuration o3 (high) + gpt-4.1

  • o3polyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-06-25

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit c48fea6; configuration o3

  • o3polyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-06-25

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit c48fea6; configuration o3 (high)

  • Claude Opus 4polyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-05-25

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit 9ef3211; configuration claude-opus-…

    225 polyglot tasks; two attempts; edit format diff; Aider commit 9ef3211; configuration claude-opus-4-20250514 (32k thinking)

  • Claude Opus 4polyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-05-25

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit 9ef3211; configuration claude-opus-…

    225 polyglot tasks; two attempts; edit format diff; Aider commit 9ef3211; configuration claude-opus-4-20250514 (no think)

  • Claude Sonnet 4polyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-05-24

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit e3cb907; configuration claude-sonne…

    225 polyglot tasks; two attempts; edit format diff; Aider commit e3cb907; configuration claude-sonnet-4-20250514 (32k thinking)

  • Claude Sonnet 4polyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-05-24

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit ef3f8bb-dirty; configuration claude…

    225 polyglot tasks; two attempts; edit format diff; Aider commit ef3f8bb-dirty; configuration claude-sonnet-4-20250514 (no thinking)

  • GPT-4.1polyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-04-14

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit 7a87db5-dirty; configuration gpt-4.…

    225 polyglot tasks; two attempts; edit format diff; Aider commit 7a87db5-dirty; configuration gpt-4.1

  • GPT-4.1 Minipolyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-04-14

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit ffb743e-dirty; configuration gpt-4.…

    225 polyglot tasks; two attempts; edit format diff; Aider commit ffb743e-dirty; configuration gpt-4.1-mini

  • o3 Minipolyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-01-31

    Scope · 225 polyglot tasks; 224 attempted cases reported; two attempts; edit format diff; Aider commit b0d58…

    225 polyglot tasks; 224 attempted cases reported; two attempts; edit format diff; Aider commit b0d58d1-dirty; configuration o3-mini (high)

  • o3 Minipolyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2025-01-31

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit 2fb517b-dirty; configuration o3-min…

    225 polyglot tasks; two attempts; edit format diff; Aider commit 2fb517b-dirty; configuration o3-mini (medium)

  • GPT-4o (2024-08-06)polyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2024-12-30

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit 09ee197-dirty; configuration gpt-4o…

    225 polyglot tasks; two attempts; edit format diff; Aider commit 09ee197-dirty; configuration gpt-4o-2024-08-06

  • GPT-4o (2024-11-20)polyglot-225

    Aider Polyglot Benchmark · Aider Polyglot Benchmark (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2024-12-30

    Scope · 225 polyglot tasks; two attempts; edit format diff; Aider commit 09ee197-dirty; configuration gpt-4o…

    225 polyglot tasks; two attempts; edit format diff; Aider commit 09ee197-dirty; configuration gpt-4o-2024-11-20

  • Aider Polyglot Benchmarkpolyglot-225

    Aider via Epoch AI

    2 models with scores · Positions withheld

    Measurement date not reported

    Scope · Edit format diff · effort high · result date not supplied

  • Aider Polyglot Benchmarkpolyglot-225

    Aider via Epoch AI

    9 models with scores · Positions withheld

    Measurement date not reported

    Scope · Edit format diff · result date not supplied

  • Aider Polyglot Benchmarkpolyglot-225

    Aider via Epoch AI

    6 models with scores · Positions withheld

    Measurement date not reported

    Scope · Edit format whole · result date not supplied

  • DeepSeek V3.2 Exppolyglot-225

    Aider Polyglot Benchmark · Aider via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Edit format diff · effort thinking · result date not supplied

  • Gemini 2.5 Pro Preview 06-05polyglot-225

    Aider Polyglot Benchmark · Aider via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Edit format diff-fenced · effort 32K · result date not supplied

  • Gemini 2.5 Pro Preview 06-05polyglot-225

    Aider Polyglot Benchmark · Aider via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Edit format diff-fenced · result date not supplied

Aider Polyglot Benchmark model results | VibeLeaderboard