SWE-bench VerifiedCoding
74.4*/ 100
Verified
Last Verified: 2026-04-22Artificial Analysis (Independent)
Resolving real-world GitHub issues. Verified subset ensures solvable issues.
Beta version: *Information might not be fully accurate. Please report any discrepancies.
Latest Data
2026-04-22
Context Window
256k
tokens
Input Cost
$0.07
per 1M tokens
Output Cost
$0.26
per 1M tokens
Parameters
295B total (21B active, MoE)
model footprint
Performance Analysis // Verified Benchmarks
Resolving real-world GitHub issues. Verified subset ensures solvable issues.
Humanity's Last Exam - Hard reasoning benchmark without tools.
Graduate-Level Google-Proof Q&A Benchmark.
Agent performance in realistic terminal workflows (v2.0 leaderboard).