Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning on HLE (Head-to-head win %)
Loading...
100
Head-to-head Win %
IG
-4
23
50
77
May 20, 2026
Head-to-head Win %
Updated 13d ago
Evaluation Results
Method
Method
Links
Head-to-head Win %
IG
Opponent=Trace2Skill
2026.05
100
IG
Opponent=RLM
2026.05
100
IG
Opponent=Single-Agent...
2026.05
100
CC Subagents
Opponent=RLM
2026.05
100
CC Subagents
Opponent=Single-Agent...
2026.05
100
Trace2Skill
Opponent=RLM
2026.05
100
Trace2Skill
Opponent=Single-Agent...
2026.05
89
CC Subagents
Opponent=Trace2Skill
2026.05
72
IG
Opponent=CC Subagents
2026.05
67
Single-Agent Coding
Opponent=RLM
2026.05
61
RLM
Opponent=Single-Agent...
2026.05
39
CC Subagents
Opponent=IG
2026.05
33
Trace2Skill
Opponent=CC Subagents
2026.05
28
Single-Agent Coding
Opponent=Trace2Skill
2026.05
11
Trace2Skill
Opponent=IG
2026.05
0
RLM
Opponent=IG
2026.05
0
RLM
Opponent=CC Subagents
2026.05
0
RLM
Opponent=Trace2Skill
2026.05
0
Single-Agent Coding
Opponent=IG
2026.05
0
Single-Agent Coding
Opponent=CC Subagents
2026.05
0
Feedback
Search any
task
Search any
task