Rank #1
Model result · rank #1
DeepSeek V4 Flash
DeepSeek direct API. Public result card with the model’s overall score, lane measurements, runtime/cost telemetry, and ranking formula.
Full rank #1
SWE rank #3
100.0% reliability
All-around publication view
Score91.38
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
Final95.80
Capability96.80
Agentic96.32
Pass rate97.7%
Prompts43
This lane captures instruction following, structured behavior, tool discipline, and general agentic reliability.
Software engineering MVP
SWE score86.95
Focused final86.59
Capability84.53
Daily driver87.04
Prompts24
This lane is closer to implementation usefulness: source handling, architecture cleanliness, and deliverable quality.
Runtime economics
Full cost$0.079
SWE cost$0.0071
Full avg seconds4.60
SWE time198.43s
Decode77.09
Cost, time, and runtime basis are telemetry. They explain tradeoffs; they do not secretly overwrite the capability scores.
Interpretation
Why this result lands here.
Rank #1 is the current all-around reference point: strong Full/Agentic performance, competitive SWE delivery, and transparent runtime telemetry.