aiaimodel.cards
← All benchmarks

SWE-bench Verified (OpenAI agentic harness)

Fixing real issues in real open-source repositories; a patch counts only if the project's own tests pass. Variants differ in task set and languages.

Your workloadRAG over docs · 12K in · 600 out · 50K requests/mo · 30% cached
  1. 1GPT-4.1 · OpenAIbest value
    55.0%

“Best value”: no other model here reports a higher score at a lower cost for your workload. Scores are self-reported by each maker with different settings, so treat close calls as ties.

How each maker reported it

  • GPT-4.1 openai/simple-evals README; Prompting Guide §1

    OpenAI's simple-evals results (zero-shot chain-of-thought, system prompt "You are a helpful assistant."). MATH is MATH-500 for models released on or after o1; OpenAI considers MGSM and DROP saturated for newer models. The repo stopped adding results in July 2025. SWE-bench Verified is OpenAI's own agentic harness result from the prompting guide.

Only each model's own maker's number is shown; scores a maker reports for rival models are left out.