LLM Digest
Subscribe

Model Release Radar

Price/capability frontier position, benchmark scores, and community signal

View as JSON

Model Release Radar

Claude Fable 5

anthropic·closed weights·Proprietary·released Tuesday, Jun 9, 2026

Frontier position
  • Behind frontier DeepSWE pass@1 (agentic coding) - Claude Opus 5, GPT-5.6 Sol are priced the same or lower and at least as capable.
Cost vs. capability

Loading chart…

Benchmark scores

Measured cost per task (DeepSWE)

BenchmarkPass@1Measured cost / taskFrontier
DeepSWE (agentic coding) (xhigh effort, 95% CI 66.7%-73.2%, 4 runs)69.9%$13.41 (median $11.34)behind

Artificial Analysis scores (no matched cost)

Artificial Analysis scores below have no measured per-task cost, so no frontier claim is made for them here.

BenchmarkScore
AA intelligence index62.1
AA coding index76.5
GPQA Diamond (science)92.6%
Humanity's Last Exam55.5%
IFBench (instruction following)63.5%
LCR76.7%
SciCode (coding)60.2%
Tau2 (tool use)98.5%
Tau2 (banking)38.1%
Terminal-Bench (hard)62.9%
Terminal-Bench 2.1 (agentic)84.6%
Community signal
VariantCoding EloOverall EloVotes
Rating1,5191,49525,824