Loading the current published AI model ranking…
Coding ranks the published roster by SWE-Bench Pro when coverage exists. Terminal-Bench 2.1 and 2.0 appear as separate companion columns only when accepted exact-variant evidence is available.
View
Quality view
Quality scores capability evidence without applying price as a direct standalone bonus or penalty. Responsiveness is scored when accepted TTFT and throughput evidence is available.
Value view
Value keeps cheap-but-weak models out with the HLE floor, then rewards qualified models that deliver more intelligence at lower standard conversation cost.
Intelligence view
Intelligence ranks the same published roster by Humanity's Last Exam in thinking mode with no tools. Supporting benchmarks stay visible, but they do not change the public axis label.
Coding view
Coding is a raw benchmark lens over the same published roster. SWE-Bench Pro determines rank, while accepted companion coding evidence stays visible when exact-variant benchmark rows are verified and does not change order.
Buyer-facing table
View explanation
Why the Coding view changes
This is a raw SWE-Bench Pro benchmark view. It changes when the published benchmark evidence changes. Terminal-Bench 2.1 and 2.0 are shown in separate companion columns only when accepted exact-variant rows are available, and they do not create a new PickAI score.
Editorial investigation
The coding leaderboard keeps the software engineering benchmark front and center, then exposes companion evidence next to it so buyers can spot harness-driven divergence quickly.
Open top coding model"The most intelligent model in the current field, but its record capability comes with roster-leading token prices, quarter-rate token throughput, and safeguard-triggered fallback routing."
Claude Fable 5
Anthropic
Anthropic
United StatesSelf-reportedTerminal-Bench 2.1
Terminal-Bench 2.0
SWE-Bench Pro
Anthropic
United StatesSelf-reported
xAI
United StatesSelf-reported
OpenAI
United StatesSelf-reportedOpenAI
United StatesSelf-reportedAnthropic
United StatesSelf-reportedOpenAI
United StatesSelf-reported
Qwen
ChinaSelf-reported
United StatesSelf-reportedUnited StatesSelf-reportedTerminal-Bench 2.1
Terminal-Bench 2.0
SWE-Bench Pro
Terminal-Bench 2.1
Terminal-Bench 2.0
SWE-Bench Pro
Terminal-Bench 2.1
Terminal-Bench 2.0
SWE-Bench Pro
Terminal-Bench 2.1
Terminal-Bench 2.0
SWE-Bench Pro
Terminal-Bench 2.1
Terminal-Bench 2.0
SWE-Bench Pro
Terminal-Bench 2.1
Terminal-Bench 2.0
SWE-Bench Pro
Terminal-Bench 2.1
Terminal-Bench 2.0
SWE-Bench Pro
Terminal-Bench 2.1
Terminal-Bench 2.0
SWE-Bench Pro
Terminal-Bench 2.1
Terminal-Bench 2.0
SWE-Bench Pro