Claude Sonnet 5 (Anthropic) vs GPT-5.6 Sol (OpenAI)

Independent benchmarks

Scores read on the public leaderboards on 2026-09-19 — no maker-reported numbers here (those live in the spec sheets below: a vendor's own harness, scaffold and pass@k make self-reported scores incomparable across vendors).

LMArena Elo comes from one arena with one voter pool, so the two cells compare directly. Terminal-Bench scores each model with the agent harness named in the cell — different harnesses, so no winner is highlighted on that row: part of the gap is the harness, not the model. Sources: tbench.ai (Apache-2.0) · LMArena (CC-BY-4.0).

What it costs at your volume

Straight token math from the verified prices above — no caching, no batch discounts. If your workload reuses prompts, cached input ($0.2 vs $0.4/1M) can shift this table substantially. Model your own traffic in the LLM cost calculator.

Neither price has moved since we started tracking them (2026-09-03). Full price history on each endpoint page.

Same weights, other hosts

The table at the top compares one endpoint per side. But the same model is often sold by several hosts — open weights re-hosted, or a closed model resold through clouds — at different prices, sometimes a bigger spread than the head-to-head itself.

claude-sonnet-5 is sold by 3 hosts we track. Cheapest: Anthropic at $12/1M blended. All 3 priced side by side on the claude-sonnet-5 page.

gpt-5.6-sol is sold by 3 hosts we track. Cheapest: OpenAI at $24/1M blended. All 3 priced side by side on the gpt-5.6-sol page.

What the makers declare

The table above compares two endpoints — what each host charges, how much of the window it serves, how fast it answers. This is the other register: what the maker declares about the weights, the same whichever host you buy from. Where a row here carries a different number from the same row above, both are true — one describes the model, the other describes the endpoint that serves it.