Rank #3
Model result · rank #3
MiniMax M3
OpenRouter · extra-high reasoning. Public result card with the model’s overall score, lane measurements, runtime/cost telemetry, and ranking formula.
Full rank #6
SWE rank #4
100.0% reliability
All-around publication view
Score86.11
Formula50% Full + 50% SWE
BasisOpenRouter · extra-high reasoning
The overall score is calculated from the Full/Agentic and SWE lanes, keeping the aggregate comparable while preserving the measurements behind it.
Full / Agentic benchmark
Final85.33
Capability89.60
Agentic81.72
Pass rate86.0%
Prompts43
This lane captures instruction following, structured behavior, tool discipline, and general agentic reliability.
Software engineering MVP
SWE score86.88
Focused final77.11
Capability86.15
Daily driver73.36
Prompts24
This lane is closer to implementation usefulness: source handling, architecture cleanliness, and deliverable quality.
Runtime economics
Full cost$0.109
SWE cost$0.048
Full avg seconds13.76
SWE time1116.23s
Decode24.33
Cost, time, and runtime basis are telemetry. They explain tradeoffs; they do not secretly overwrite the capability scores.
Interpretation
Why this result lands here.
This is a top-tier all-around entrant: the aggregate score remains close to the leader, with lane-level tradeoffs shown separately.