FrontierSWE

Software-engineering agent benchmark targeting frontier-level implementation, performance optimization, and research tasks.

13rows
avg_rankprimary metric
2026-05-28sampled

Metadata

ID
frontierswe
Category
Coding
Release
Unknown

Metrics

Average Rank (lower is better), Dominance, Implementation Average Rank (lower is better), Performance Average Rank (lower is better), Research Average Rank (lower is better)

Showing 2 latest source slices.

Latest Results

Provider-published system-card benchmark scores parsed from Anthropic's Claude Opus 4.8 capability evaluation tables. Rows are marked self-reported and should be interpreted as source claims unless independently reproduced.

Rank Subject Average Rank Model Match Provenance Sampled
1 Claude Opus 4.8 2.7 avg rank Claude Opus 4.8
anthropic-claude-opus-4.8
 		Self-reported 2026-05-28
2 Claude Opus 4.7 4.2 avg rank Claude Opus 4.7
anthropic-claude-opus-4.7
 		Self-reported 2026-05-28
3 Claude Opus 4.6 4.9 avg rank Claude Opus 4.6
anthropic-claude-opus-4.6
 		Self-reported 2026-05-28
1 GPT-5.5 (Codex) 2.53 avg rank / 83% dominance — Imported 2026-05-28
2 Claude Opus 4.7 (Claude Code) 3.56 avg rank / 72% dominance — Imported 2026-05-28
3 Claude Opus 4.6 (Claude Code) 4.18 avg rank / 65% dominance — Imported 2026-05-28
4 GPT-5.4 (Codex) 4.29 avg rank / 63% dominance — Imported 2026-05-28
5 Composer 2.5 (Cursor CLI) 5.71 avg rank / 48% dominance — Imported 2026-05-28
6 Gemini 3.1 Pro (Gemini CLI) 5.79 avg rank / 47% dominance — Imported 2026-05-28
7 DeepSeek V4 Pro (Claude Code) 6.76 avg rank / 36% dominance — Imported 2026-05-28
8 Kimi K2.6 (Kimi CLI) 7.12 avg rank / 32% dominance — Imported 2026-05-28
9 Kimi K2.5 (Kimi CLI) 7.41 avg rank / 29% dominance — Imported 2026-05-28
10 Qwen3.6-Plus (Qwen Code) 7.65 avg rank / 26% dominance — Imported 2026-05-28