Answer: The Aider polyglot coding leaderboard lists many models with their percent correct scores, led by gpt-5 (high) at 88.0%, followed by gpt-5 (medium) at 86.7%, o3-pro (high) at 84.9%, and gemini-2.5-pro-preview-06-05 (32k think) at 83.1%. Status: Confirmed Entry: tool/aider/models/polyglot-leaderboard-models-scores Revision: 1 Digest: sha256:68592f833d465986 (changes whenever the content changes) Timeline: Created: 2026-11-13T02:56:19Z Last changed: 2026-11-13T02:56:19Z Last verified: 2026-11-20T11:42:41Z Next check: 2026-11-21T11:42:41Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Unit | Source | As of gpt-5 (high) score | 88.0% | % | [1] | 2026-11-20 gpt-5 (medium) score | 86.7% | % | [1] | 2026-11-20 o3-pro (high) score | 84.9% | % | [1] | 2026-11-20 gemini-2.5-pro-preview-06-05 (32k think) score | 83.1% | % | [1] | 2026-11-20 gpt-5 (low) score | 81.3% | % | [1] | 2026-11-20 o3 (high) score | 81.3% | % | [1] | 2026-11-20 grok-4 (high) score | 79.6% | % | [1] | 2026-11-20 last updated | November 20, 2025 | | [1] | 2026-11-20 Sources: [1] Aider. "aider.chat/docs/leaderboards/". https://aider.chat/docs/leaderboards/ Role: primary. Accessed: 2026-11-20T11:42:41Z Quote: "gpt-5 (high) 88.0% $29.08" (Supports: gpt-5 (high) score) Quote: "gpt-5 (medium) 86.7% $17.69" (Supports: gpt-5 (medium) score) Quote: "o3-pro (high) 84.9% $146.32" (Supports: o3-pro (high) score) Quote: "gemini-2.5-pro-preview-06-05 (32k think) 83.1% $49.88" (Supports: gemini-2.5-pro-preview-06-05 (32k think) score) Quote: "gpt-5 (low) 81.3% $10.37" (Supports: gpt-5 (low) score) Quote: "o3 (high) 81.3% $21.23" (Supports: o3 (high) score) Quote: "grok-4 (high) 79.6% $59.62" (Supports: grok-4 (high) score) Quote: "last updated November 20, 2025" (Supports: last updated) Published: 2026-04-25T16:45:23Z Snapshot SHA-256: cea6cab3ac65e4d41cce072fcac5540497d757b3a6f72d997b7c3607b44c470e (captured 2026-11-13T02:56:19Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-13T02:56:19Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T11:42:41Z. No independent second source is configured for this entry Last successful check: 2026-11-20T11:42:41Z Last attempt: 2026-11-20T11:42:41Z Notes and limitations: Extracted automatically from a single official source (section "Aider polyglot coding leaderboard"). Related: https://latestn.com/tool/aider/models/reasoning-effort-setting How do I enable reasoning effort for a reasoning model in Aider? https://latestn.com/tool/aider/models/reasoning-models-other-providers Can I use reasoning models from other providers with Aider's OpenAI configuration? https://latestn.com/tool/aider/models/select-bedrock-model How do I select an Amazon Bedrock model in Aider? https://latestn.com/tool/aider/models/local-model-context-quantization How do I fix Aider edit errors with local models related to context window and quantization? https://latestn.com/tool/aider/models/models-supporting-infinite-output Which models support infinite output in Aider? https://latestn.com/tool/aider/models/openrouter-provider-selection How do I control which OpenRouter provider Aider uses for a model? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T02:56:19Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/aider/models/polyglot-leaderboard-models-scores/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/aider/models/polyglot-leaderboard-models-scores POST: https://latestn.com/dispute/tool/aider/models/polyglot-leaderboard-models-scores with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/aider/models/polyglot-leaderboard-models-scores?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). What models are on the Aider polyglot coding leaderboard and what are their scores? Revision 1, last verified 2026-11-20T11:42:41Z. https://latestn.com/tool/aider/models/polyglot-leaderboard-models-scores (accessed 2026-11-21T10:07:12Z). @misc{LatestN_tool_aider_models_polyglot_leaderboard_models_scores_r1, title = {What models are on the Aider polyglot coding leaderboard and what are their scores?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/aider/models/polyglot-leaderboard-models-scores}}, note = {Revision 1; digest sha256:68592f833d465986; last verified 2026-11-20T11:42:41Z; accessed 2026-11-21T10:07:12Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/aider/models/polyglot-leaderboard-models-scores