Standard Compute
← All models

Best Model for Aider

Claude Sonnet 5.5 is the best everyday model for Aider: it scores 61.8% on Terminal-Bench 4.0, within about three points of Claude Opus 5.5, at half the price ($5.33 per 100 coding-agent requests on our measured traffic). Aider's own polyglot leaderboard was last updated in November 2025 and does not include current models, so these picks rely on Terminal-Bench 4.0 and Scale's SWE-Bench Pro V2. Architect mode lets you pair a planning model with a separate editor model, for example Opus 5.5 as architect and Sonnet 5.5 or Claude Haiku 5.5 as editor.

Read the full Aider review → · updated 2026-10-17

Sources: Aider leaderboards · Aider chat modes · Terminal-Bench 4.0 leaderboard · Scale SWE-Bench Pro V2 · Anthropic on Haiku 5.5 · Cost per request methodology

Run any of these models in your agent

Or let the router send each step to the cheapest model that can do it, on providers we vet for price, uptime and speed. Plans from $19 a month.

Aider setup →See plans
#1Claude Sonnet 5.5Anthropic · $4.40/1M · 1M ctx

Best overall. 61.8% on Terminal-Bench 4.0 and 95.8 on Scale's SWE-Bench Pro V2, with a 1M-token context that holds a large repo map. A strong main model and a reliable editor model.

Overall 96/100 · Value 59Full breakdown →
#2Claude Opus 5.5Anthropic · $8.80/1M · 1M ctx

Best for long agent runs. #1 on Terminal-Bench 4.0 at 64.9%. A natural architect in architect mode, where it plans and a cheaper editor model writes the edits.

Overall 98/100 · Value 51Full breakdown →
#3GPT-6.1 SolOpenAI · $4.40/1M · 1.1M ctx

OpenAI pick. 96.1 on Scale's SWE-Bench Pro V2, just above Sonnet 5.5's 95.8, and 58.2% on Terminal-Bench 4.0 at the same $2/$10 list price.

Overall 92/100 · Value 58Full breakdown →
#4Claude Haiku 5.5Anthropic · $0.22/1M · 1M ctx

Best value. Anthropic reports 39.2% on Terminal-Bench 4.0 and Scale lists 87.2 on SWE-Bench Pro V2, at $0.10/$0.50 per million tokens. A cheap editor model while prompts stay under 100K tokens.

Overall 82/100 · Value 97Full breakdown →
#5DeepSeek V4.1 FlashDeepSeek · $0.22/1M · 1.0M ctx

Budget pick. Open weights at $0.30/$1.20 per million tokens at peak hours and half off-peak. DeepSeek reports 42.3% on Terminal-Bench 4.0 for its October 17 update, up from 31.2%, so check its diffs on hard changes.

Overall 77/100 · Value 93Full breakdown →
#6GLM 5.3Z.AI · $1.50/1M · 1.0M ctx

Open-weight pick. The top open-weight model on Terminal-Bench 4.0 (41.8%) and 95.6 on SWE-Bench Pro V2, with a 1M-token context.

Overall 83/100 · Value 69Full breakdown →

What 100 Aider requests cost on each pick

A typical request sends 99,534 input tokens, 87% of them read from cache, and a median session runs 16 requests. Measured on pooled coding-agent requests through our gateway (79,301 requests from 75 users; Aider alone has fewer than 50 users, so its traffic is pooled), Sep 13 to Oct 12, 2026, priced at each vendor's list rates.

Model100 requestsMedian sessionMonth of regular use
Claude Sonnet 5.5$5.33$0.74$77.42
Claude Opus 5.5$10.66$1.47$155
GPT-6.1 Sol$6.74$0.74$90.04
Claude Haiku 5.5$1.31$0.096$17.73
DeepSeek V4.1 Flash$0.67$0.091$9.13
GLM 5.3$5.72$0.71$92.16

Month of regular use = the median user active on 5 or more days (1,478 requests in 30 days). Methodology · All models ranked by cost per request

Best model for Aider under $19, $49 or $99 a month

The highest-rated model whose list-price cost for a month of regular use (1,478 requests) stays under each budget. Heavier months cost proportionally more.

Monthly budgetBest model that fitsEst. month
Under $19Claude Haiku 5.5$17.73
Under $49Claude Haiku 5.5$17.73
Under $99Claude Sonnet 5.5$77.42

"Highest-rated" uses our editorial quality and agentic scores; candidates are current models with a checked vendor price.

FAQ

What is the best model for Aider?
Claude Sonnet 5.5 for everyday work (61.8% on Terminal-Bench 4.0 at $2/$10 per million tokens), Claude Opus 5.5 for the hardest changes (64.9%), and GPT-6.1 Sol if you prefer OpenAI (96.1 on Scale's SWE-Bench Pro V2).
Is Aider's leaderboard up to date?
Aider's polyglot leaderboard was last updated on November 20, 2025, so it does not cover the Claude 5.5, GPT-6 or GLM 5.3 models. Terminal-Bench 4.0 and Scale's SWE-Bench Pro V2 are the most current public boards for coding agents.
How does Aider's architect mode use two models?
In architect mode (--architect), your main model proposes the change and an editor model, set with --editor-model, turns it into file edits. That lets a strong model such as Opus 5.5 plan while a cheaper one such as Sonnet 5.5 or Haiku 5.5 writes the diffs, at the cost of two requests per turn.
Are Claude Opus 4.8 and GPT-5.5 still the top Aider models?
No. Their successors score higher for less: Opus 5.5 scores 64.9% on Terminal-Bench 4.0 to Opus 4.8's 23.6% at $4/$20 per million tokens against $5/$25, and GPT-6.1 Sol lists at $2/$10 against GPT-5.5's $5/$30.
How much do 100 Aider requests cost?
At vendor list prices, 100 average coding-agent requests cost: Claude Sonnet 5.5 $5.33, Claude Opus 5.5 $10.66, GPT-6.1 Sol $6.74, Claude Haiku 5.5 $1.31, DeepSeek V4.1 Flash $0.67, GLM 5.3 $5.72. Measured on real coding-agent traffic through the Standard Compute gateway (Sep 13 to Oct 12, 2026), priced with each request's own token counts and cache reads.
What is the best model for Aider on a $19, $49 or $99 monthly budget?
For a month of regular use (1,478 requests, the median in our data), the highest-rated model that fits under $19: Claude Haiku 5.5 (about $17.73); under $49: Claude Haiku 5.5 (about $17.73); under $99: Claude Sonnet 5.5 (about $77.42). Heavier months cost proportionally more.

The agent matters as much as the model. Compare AI agents →

Every model on this page runs on Standard Compute

Standard Compute

Current frontier models Claude Fable 5.1 · GPT-6 Astra

More intelligence
per dollar.

Each step goes to the cheapest model that can do it, on providers we vet for price, uptime and speed, with automatic fallback when one fails.

Compliance
Opt-in rules keep a company, team or key on European or US providers
Privacy
We don’t train on your prompts or store them

Fixed monthly plans from $19 · cancel anytime

7-day fair refund Free trial, no card Billing by Stripe4,100+ agent users