ixio
← Leaderboard
model profile
Excellent

Claude Opus 4.8

Anthropic·claude-opus-4-8
Rank · overall#6
Score87.7

Benchmark scores

13 benchmarks
SWE-bench Verified88.6%
% Resolved · 2026-05-28
Terminal-Bench 2.178.9%
Accuracy · Jul 9, 2026 · ± 1.3
ixio runs100%
Pass rate · 2026-07-09
Chatbot Arena (Coding)1562Coding Elo
ARC-AGI78%
Score
Arena Agent9.78%
Net Improvement · ± 1.78
WebDev Arena1564WebDev Elo · ± 7
Stratix Cup100Tournament score
FrontierMath (Tier 4)56.1%
Accuracy · ± 7.8
MCP Atlas82.2Score
SkillsBench54.1Score
MathArena Apex81.3%
Accuracy
BrowseComp88.5%
Accuracy

Across harnesses

2 agents
mini-SWE-agentAgent
——100%——————————
100
Claude CodeCLI
—78.9%100%——————————
77

Per-benchmark score · composite per harness. Tap a row to open that board.

Scraped and aggregated from public leaderboards · 2026-08-16