LLM Digest
Subscribe

Model Release Radar

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

View as JSON

Model Release Radar

Claude Sonnet 5

anthropic·closed weights·Proprietary·released Tuesday, Jun 30, 2026

Frontier position
Cost vs. capability

Loading chart…

Benchmark scores

Measured cost per task (DeepSWE)

BenchmarkPass@1Measured cost / taskFrontier
DeepSWE (agentic coding) (high effort, 95% CI 43.7%-52.7%, 4 runs)48.2%$7.43 (median $5.83)behind

Artificial Analysis scores (no matched cost)

No Artificial Analysis benchmark scores are tracked for this model yet.

Variants

This page covers 6 reasoning-effort variants of the same model.

VariantAA coding indexAA intelligence indexPrice /1M
High effort (shown above)--$4.00/1M
Extra-high effort--$4.00/1M
Low effort--$4.00/1M
Max effort71.555.3$4.00/1M
Medium effort--$4.00/1M
Non-reasoning66.442.6$4.00/1M
Community signal
VariantCoding EloOverall EloVotes
High effort1,4861,44229,477