readable AI benchmarks (simplified)

readable AI benchmarks

Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) has a Quality Score of 82.3, ranking 1st 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 71.7, ranking 1st among 272 scored models, above average (total average: 34.1). Its Value Score is 47.2, high compared with the total Value average of 28.2.

Quality Score82.3coverage 91.2%: missing Epoch General ECI, CursorBench 3.2 and DeepSWE v1.1

Value Score47.2

Reliability71.7

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: $3.69

Capability

Intelligence: 65.7
Coding: 81.6
Agentic: 61.3
Omniscience: 43.5
Correct: 67.2%
Blended price: $7.18

Answer outcomes

Attempt rate: 91.0%

Correct 67.2%Incorrect 23.8%Abstained 9.0%

Artificial Analysis benchmarks

GDPval-AA v2: 68%
τ³-Banking: 47%
Terminal-Bench v2.1: 91%
SciCode: 62%
Humanity’s Last Exam: 59%
GPQA Diamond: 94%
CritPt: 30%
AA-Omniscience: 72%
AA-LCR: 80%

Similar models

Graph Open on Artificial Analysis