agentic Coding LEADERBOARDS

Coding benchmarks for real-world software engineering

Explore benchmarks that test coding agents on the work software engineers actually do, from navigating complex codebases and debugging failures to shipping features and maintaining code quality over time.

partners
Standford logo
Image
Image
Image
Image
Image
Image
Image
agent-le-logo
Image
Image
Cua Logo
Open Benchmarks Grants

Senior SWE-bench

Evaluates coding agents on senior-level software engineering tasks.

Built with
Image
Image
Image
Tasteful Solve Rate
The top-performing frontier models fail to complete tasks with senior-level correctness and taste over 65% of the time.
Consistent reward hacking (e.g. copying fixes from newer PyPI/npm releases) detected, 5 tasks removed from score
Image
Opus 5.5
39.3%
2
Image
GPT-6 Astra
36.8%
3
Image
Fable 5.1
34.7%
4
Image
Fable 5
34.7%
Archived
, 
Open Benchmarks Grants

Agents’ Last Exam

Evaluating AI agents on long-horizon, economically valuable professional workflows with verifiable outcomes.

By Pass Rate
1
Image
Opus 5.5
38.2%
2
Image
GPT-6 Astra
34.2%
3
Image
GPT-6 Sol
32.2%
4
Image
Claude Opus 5
32.2%
Open Benchmarks Grants

SlopCode Bench

Measures coding-agent performance across evolving software requirements.

By Iso Solve
1
Image
GPT-5.5
28.06%
2
Image
GPT-5.3
26.02%
3
Image
GPT-5.4
23.47%
4
Image
GPT 5.2
21.94%
Open Benchmarks Grants

Terminal-Bench 3.0

Evaluates terminal agents on containerized tasks across seven domains.

By Resolution Rate
1
Image
Opus 5
42.7%
2
Image
GPT-5.6 Sol
34.6%
3
Image
Fable 5
34.1%
4
Image
GLM 5.3
32.4%
Archived

Terminal-Bench 2.1

Terminal agent evaluation led by Stanford University and Laude Institute. v2.1 fixes 28 tasks from 2.0 and introduces continuous validation.

Top Submissions
1
Image
GPT-6 Astra (high) · Codex
87.4%
2
Image
Fable 5 (xhigh) · Claude Code
83.8%
3
Image
GPT-5.5 (xhigh) · Codex
83.2%
Archived

Agentic Coding

A benchmark for evaluating AI models on complex, real-world coding tasks that require multi-step reasoning, tool use, and autonomous problem-solving.

Top Models
1
Image
Claude Opus 4.6
65.2%
2
Image
Claude Opus 4.5
58.0%
3
Image
Claude Sonnet 4.5
57.6%
Agentic coding resources

Learn more

A curated collection of blogs, research papers, and reading-group discussions on agentic coding benchmarks, covering benchmark design, realistic coding environments, model performance, and the failure modes shaping what comes next.

coding-agents-eval

Why coding agents need better data, evals, and environments

Coding agents have moved from tab-complete to teammate. They autonomously inspect repositories, edit files, run commands, diagnose failures, and work through multi-step engineering tasks. That creates a harder reliability problem.
May 11, 2026
•
Justin Bauer
senior-swe-reading-group

Senior SWE-Bench: Evaluating Coding Agents Like Senior Engineers

At our latest Snorkel AI Reading Group, Henry Ehrenberg presented Senior SWE-Bench, an open-source, Harbor-compatible benchmark for evaluating coding agents on realistic, senior-level software engineering work. Its 100 tasks, with
July 16, 2026
•
Team Snorkel
Building the Benchmark Factory Banner

Benchtalks #1: Alex Shaw (Terminal-Bench, Harbor) – Building the Benchmark Factory

To kick off our inaugural Benchtalks, a series dedicated to the researchers building these measurement toolkits, Snorkel AI co-founder Vincent Sunn Chen sat down with Alex Shaw, Founding MTS at
March 31, 2026
•
Vincent Sunn Chen
Image

Claude Opus 5: Performance and Error Analysis on Frontier Coding Tasks

Anthropic’s Claude Opus 5 recently debuted as the second model overall on the current Senior SWE-bench leaderboard, behind Fable 5. It also achieves the highest score of any evaluated model
July 27, 2026
•
Ankit Aich
Closing the Evaluation Gap in Agentic AI Image

Closing the Evaluation Gap in Agentic AI

Today, AI is marked by a growing asymmetry: the excitement around agentic AI is real — backed by quantitative progress on model cards and genuine leaps forward, especially in coding.
February 11, 2026
•
Vincent Sunn Chen
Image

SlopCodeBench: Measuring Code Erosion as Agents Iterate

SlopCodeBench reveals how AI coding agents degrade code quality over time—measuring “slop,” technical debt, and architectural erosion across iterations.
January 20, 2026
•
Kobie Crawford
Image

The science of rubric design

Part 3 of our rubric series explains the science of rubric design. We show why rubrics should be treated like models—structured, measured, and iterated—to maximize objective alignment and inter-rater agreement.
September 11, 2025
•
Charles Dickens
,
Chris Glaze
Image

Cua-Bench: benchmarking computer-use agents on professional software

TL;DR We built a benchmark of 25 expert-authored KiCad schematic-editing tasks and ran a frontier computer-use agent against them. The headline numbers: 1. Why build a computer-use benchmark for electrical
June 15, 2026
•
Zhengyang (Jason) Qi
,
Armin Parchami
of
Illution Back
Illution Front

For models that need to be right. Not just good enough.

Request dataset samples
Explore research