Rank #5
Model result · rank #5
Claude Opus 4.8
OpenRouter · extra-high reasoning · Hard Intelligence. Public result card with the model’s overall score, lane measurements, runtime/cost telemetry, and ranking formula.
Full rank #13
SWE rank #3
Hard rank #7
100.0% reliability
All-around publication view
Score84.45
Formulamean(Full, SWE, Hard Intelligence)
BasisOpenRouter · extra-high reasoning · Hard Intelligence
The overall score averages the measured major lanes while keeping each source measurement visible.
Full / Agentic benchmark
Final83.32
Capability94.37
Agentic94.68
Pass rate93.0%
Prompts43
This lane captures instruction following, structured behavior, tool discipline, and general agentic reliability.
Software engineering MVP
SWE score88.67
Focused final84.92
Capability87.69
Daily driver83.74
Prompts24
This lane is closer to implementation usefulness: source handling, architecture cleanliness, and deliverable quality.
Hard Intelligence diagnostic
Hard score81.37
Active inquiry93.08
Online adaptation80.00
Self-repair82.40
Authority integrity70.00
Hard Intelligence measures active inquiry, online adaptation, evidence-driven self-repair, and authority/salience integrity.
Runtime economics
Total cost$6.115
Cost / scored item$0.082
Seconds / timed item10.43s
Runtime coverage100.0%
Recorded tokens / item12.0k
Token coverage100.0%
Cost, time, and token basis are normalized telemetry. They explain tradeoffs; they do not overwrite the capability score yet.
Interpretation
Why this result lands here.
The result is best read as a balanced benchmark entry: one overall score plus the lane measurements that produced it. Hard Intelligence score is 81.37 and contributes to the overall score alongside Full/Agentic and SWE. Hard Intelligence is published alongside Full/Agentic and SWE for the current ranking.