Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM
Build or fix software · Build an application or service

Best AI model for coding — September 2026

On BenchLM's public evidence, Claude Fable 5.1 has the highest coding score estimate among the models that meet this page's constraints (83.8). Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Shortlist data updated

Share this shortlist

Share on XLinkedIn

This address is permanent. It always shows the current shortlist for this job, with the date the data was last updated. The embed shows the same shortlist on your site and links back here.

The shortlist for coding

Constraints on this page: a builder choosing by accuracy, hosted processing allowed, any price, ordinary input size. Change any of them under Refine. A small score gap does not establish a reliably better model.

Compare Claude Fable 5.1 vs Claude Fable 5Full coding leaderboard

  1. 01Claude Fable 5.1Best fit

    Anthropic · Proprietary

    83.8

    Coding score estimate

    • Highest coding estimate among models that meet every stated constraint
    • $20.00 for the stated workload
    • 1M context

    Estimate sources: LMArena Code Overall, Artificial Analysis, LiveBench Coding, Vals AI coding-task composite

    Model page and evidence

  2. 02Claude Fable 5

    Anthropic · Proprietary

    76.9

    Coding score estimate

    • Estimate 76.9 on the same coding evidence
    • $20.00 for the stated workload
    • 1M context

    Estimate sources: LMArena Code Overall, Artificial Analysis, LiveBench Coding, Vals AI coding-task composite

    Model page and evidenceCompare with Claude Fable 5.1

  3. 03Claude Opus 5

    Anthropic · Proprietary

    75.6

    Coding score estimate

    • Estimate 75.6 on the same coding evidence
    • $10.00 for the stated workload

    Estimate sources: LMArena Code Overall, Artificial Analysis, LiveBench Coding, Vals AI coding-task composite

    Model page and evidenceCompare with Claude Fable 5.1

  4. 04GPT-6 Astra

    OpenAI · Proprietary

    74.4

    Coding score estimate

    • Estimate 74.4 on the same coding evidence
    • $20.00 for the stated workload
    • 1.05M context

    Estimate sources: Artificial Analysis, LiveBench Coding, Vals AI coding-task composite

    Model page and evidenceCompare with Claude Fable 5.1

  5. 05GPT-5.6 Sol

    OpenAI · Proprietary

    74.3

    Coding score estimate

    • Estimate 74.3 on the same coding evidence
    • $8.00 for the stated workload
    • 1.05M context

    Estimate sources: LMArena Code Overall, Artificial Analysis, LiveBench Coding, Vals AI coding-task composite

    Model page and evidenceCompare with Claude Fable 5.1

Refine for your situation

Each link opens the selector with one answer changed. The address carries the answers, so your version is as shareable as this page.

A decision model maps your sentence to the selector’s questions. The shortlist comes from public evidence only, and nothing is stored.

What this shortlist rests on

The coding surface. Each model’s estimate names its own sources above; these are the public weighted benchmarks for the category.

What to verify before choosing

  • Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
  • Composite scores are estimates. A small score gap does not establish a reliably better model.

Try three representative examples of your own work. Compare errors, time, cost, and the tools available in your actual setup.

Questions

Which AI model is best for coding?

On BenchLM's public evidence, Claude Fable 5.1 by Anthropic has the highest coding score estimate among models that meet the page's default constraints (83.8). Ordered by task score under the stated constraints. Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

What are the alternatives to Claude Fable 5.1 for coding?

Claude Fable 5 (76.9), Claude Opus 5 (75.6), GPT-6 Astra (74.4), GPT-5.6 Sol (74.3) follow on the same evidence. A small gap does not establish a reliably better model; compare them on three representative examples of your own work.

How does BenchLM pick the best ai model for coding?

The page runs the LLM Selector with fixed answers: a builder choosing by accuracy, hosted processing allowed, any price, ordinary input size. The selector uses the coding evidence surface, filters by the stated constraints, and orders by that evidence. It never adds a hidden fit score or a bonus for open weights or reasoning style.

Can I change the constraints?

Yes. Every link under "Refine" opens the selector with one answer changed, and the address carries the answers so a result can be shared or reopened against the current dataset.

Method: bench-align-v5.5-2026-09-04. Read the methodology and benchmark confidence pages for how scores and verification statuses are produced.

Watch the coding shortlist

One weekly email when rank, price, or benchmark evidence changes make this shortlist worth revisiting.

Read a sample issue

Join 2,000+ readers.