Rank #5
Model result · rank #5
DeepSeek V4 Pro
DeepSeek direct API. Public result card with the model’s overall score, lane measurements, runtime/cost telemetry, and ranking formula.
Full rank #2
SWE rank #7
100.0% reliability
All-around publication view
Score85.86
Formula50% Full + 50% SWE
BasisDeepSeek direct API
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
Final92.04
Capability99.37
Agentic97.18
Pass rate100.0%
Prompts43
This lane captures instruction following, structured behavior, tool discipline, and general agentic reliability.
Software engineering MVP
SWE score79.68
Focused final65.14
Capability75.75
Daily driver60.42
Prompts24
This lane is closer to implementation usefulness: source handling, architecture cleanliness, and deliverable quality.
Runtime economics
Full cost$0.248
SWE cost$0.033
Full avg seconds10.40
SWE time696.70s
Decode37.73
Cost, time, and runtime basis are telemetry. They explain tradeoffs; they do not secretly overwrite the capability scores.
Interpretation
Why this result lands here.
The model is stronger in the Full/Agentic lane than in the SWE lane; the overall score is therefore shown with both component lanes visible.