readable AI benchmarks (simplified)

readable AI benchmarks

Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) has a Quality Score of 79.6, ranking 4th among 272 scored models. Per 1M tokens, pricing is $10.00 input, $50.00 output, $0.250 cached input, and $12.50 cached output. It accepts text and image input, outputs text, and has a 1M token context window. Its Reliability Score is 70.4, ranking 4th among 272 scored models, above average (total average: 34.1). Its Value Score is 45.4, high compared with the total Value average of 28.2.

Quality Score79.6coverage 91.2%: missing Epoch General ECI, CursorBench 3.2 and DeepSWE v1.1

Value Score45.4

Reliability70.4

Cache Discount98%

Model specification

Reasoning: reasoning
Input modalities: text, image
Output modalities: text
Context window: 1M tokens
Weights: closed weights

Token prices USD per 1M tokens

Input: $10.00
Output: $50.00
Cached Input: $0.250
Cached Output: $12.50
Cost per task: $1.43

Capability

Intelligence: 62.5
Coding: 79.1
Agentic: 55.8
Omniscience: 40.8
Correct: 64.9%
Blended price: $7.18

Answer outcomes

Attempt rate: 89.1%

Correct 64.9%Incorrect 24.1%Abstained 10.9%

Artificial Analysis benchmarks

GDPval-AA v2: 62%
τ³-Banking: 43%
Terminal-Bench v2.1: 90%
SciCode: 58%
Humanity’s Last Exam: 56%
GPQA Diamond: 91%
CritPt: 30%
AA-Omniscience: 70%
AA-LCR: 77%

Similar models

Graph Open on Artificial Analysis