Global AI Search

Search the entire AI Orbit.

Find tools, models, companies, news, guides, comparisons and benchmark data from one research-driven index.

391 matching results for “Debugging”

Discovery pathsRelated categories, features and use cases

Explore use caseDebugging Explore featureCode Review & Debugging Browse categoryCoding & Development

Benchmarks

24 matches

View benchmark hub

Research

Internal Research Debugging Evaluation

percentage

Internal Research Debugging Evaluation — official/provider-reported evaluation result. Methodology conditions ar...

Code Review

Martian Code Review Bench — Online F1

Live snapshot 2026-08-28

Living open-source code-review benchmark based on real-world pull-request behavior; F1 balances precision and re...

Code Review

Martian Code Review Bench — Offline F1

2026-06-24

Controlled code-review benchmark across 50 hard-to-find bugs; F1 balances precision and recall.

Coding

LiveCodeBench

percentage

LiveCodeBench — official/provider-reported evaluation result. Methodology conditions are preserved in the result...

Coding

LiveCodeBench v6

percentage

LiveCodeBench v6 — official/provider-reported evaluation result. Methodology conditions are preserved in the res...

Coding

Codeforces Percentile

percentage

Codeforces Percentile — official/provider-reported evaluation result. Methodology conditions are preserved in th...

Robotics

Helix Logistics — Barcode Success Rate

Helix S1 | 60h demonstrations

Figure's public controlled evaluation of Helix S1 logistics manipulation after scaling demonstration data; score...

Search & Retrieval

Exa WebCode Contents — Extraction Accuracy

Open benchmark snapshot 2026-08-28

Accuracy on Exa's open WebCode Contents track measuring extraction fidelity against golden markdown.

Coding

HumanEval

percentage

Software Engineering

SWE-bench Verified — Agent Systems

Verified

Human-validated 500-instance SWE-bench subset used to evaluate coding agents and systems.

Coding

SWE-bench Verified (OpenAI 477 Tasks)

percentage

SWE-bench Verified (OpenAI 477 Tasks) — official/provider-reported evaluation result. Methodology conditions are...

Coding

Aider Polyglot (Diff)

percentage

Aider Polyglot (Diff) — official/provider-reported evaluation result. Methodology conditions are preserved in th...

Coding

SWE-Bench Pro

percentage

SWE-Bench Pro — official/provider-reported evaluation result. Methodology conditions are preserved in the result...

Coding

Terminal-Bench 2.1

percentage

Terminal-Bench 2.1 — official/provider-reported evaluation result. Methodology conditions are preserved in the r...

Coding

SWE-bench Verified (Anthropic Full 500)

percentage

SWE-bench Verified (Anthropic Full 500) — official/provider-reported evaluation result. Methodology conditions a...

Coding

SWE-bench Verified (Anthropic Full 500 High Compute)

percentage

SWE-bench Verified (Anthropic Full 500 High Compute) — official/provider-reported evaluation result. Methodology...

Coding

Terminal-bench

percentage

Terminal-bench — official/provider-reported evaluation result. Methodology conditions are preserved in the resul...

Coding

SWE-bench Verified (Anthropic 489 Internal Subset)

percentage

SWE-bench Verified (Anthropic 489 Internal Subset) — official/provider-reported evaluation result. Methodology c...

Coding

SWE-bench Verified (Anthropic 489 High Compute)

percentage

SWE-bench Verified (Anthropic 489 High Compute) — official/provider-reported evaluation result. Methodology cond...

Coding

Aider Polyglot

percentage

Aider Polyglot — official/provider-reported evaluation result. Methodology conditions are preserved in the resul...

Coding

SWE-bench Verified (Google Single Attempt)

percentage

SWE-bench Verified (Google Single Attempt) — official/provider-reported evaluation result. Methodology condition...

Coding

SWE-bench Verified (Google Multiple Attempts)

percentage

SWE-bench Verified (Google Multiple Attempts) — official/provider-reported evaluation result. Methodology condit...

Coding

SWE-bench Verified (DeepSeek Resolved)

percentage

SWE-bench Verified (DeepSeek Resolved) — official/provider-reported evaluation result. Methodology conditions ar...

Coding & Terminal Agents

Terminal-Bench 4.0

percentage

Publicly reported coding & terminal agents benchmark result.