Independent intelligence

Comparison.

A benchmark snapshot of the leading models available in Benaiah. Choose any bar to use or unlock that intelligence.

About this data

Snapshot updated 4 August 2026.

Source: Artificial Analysis, Intelligence Index v4.1.
Speed: Reported output tokens per second. Throughput varies by provider load and configuration.
Cost: Weighted average provider cost per Intelligence Index task, converted from USD at £0.7489 per $1 using the 23 July 2026 ECB reference rate.

Benchmarks are a decision aid, not a guarantee for every prompt. This is a maintained snapshot rather than a live feed.

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Cost per task

Weighted average cost in GBP · Lower is better

■ Model Recommender

Personalised recommendations based on your priorities.

Step 1 of 5

Set your priorities

Move the sliders to set how important each factor is.

Intelligence Model capability based on Artificial Analysis Intelligence Index. Very important Speed Output speed of endpoints serving the model. Low importance Cost Cost per Intelligence Index task in Benaiah’s snapshot. Low importance

Top recommendations

Model	Intelligence	Speed	Context	Task cost	Input	Output