ixio
← Leaderboard
model profile
Excellent

GPT-5.5

OpenAI·gpt-5-5
Rank · overall#10
Score85.9

Benchmark scores

13 benchmarks
SWE-bench Verified82.6%
% Resolved · 2026-04-23
Terminal-Bench 2.183.1%
Accuracy · May 1, 2026 · ± 1.1
ixio runs100%
Pass rate · 2026-07-09
Chatbot Arena (Coding)1561Coding Elo
ARC-AGI85%
Score
Arena Agent8.9%
Net Improvement · ± 1.03
WebDev Arena1507WebDev Elo · ± 6
Stratix Cup76.4Tournament score
FrontierMath (Tier 4)72.5%
Accuracy · ± 7.1
MCP Atlas75.3Score
SkillsBench67.3Score
MathArena Apex80.2%
Accuracy
BrowseComp84.4%
Accuracy

Across harnesses

3 agents
Claude CodeCLI
——100%——————————
100
Codex CLICLI
—83.1%———————————
94
Terminus 2Agent
—78%———————————
65

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

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