Quality
How claude-opus-4-6-thinking compares against every tracked model
Composite of GPQA Diamond, MATH / AIME, SWE-bench Verified, LiveBench, Humanity's Last Exam and Terminal-Bench, normalised 0–100. Scores are ingested from their publishers; we do not run these evaluations.
Quality Breakdown
claude-opus-4-6-thinking on each evaluation feeding the index, against the tracked average
Bar = claude-opus-4-6-thinking · grey marker = average across tracked models
None of the six index evaluations have published a score for this model yet.
Arena Elo
Human preference rating from blind pairwise votes
Elo from blind pairwise votes, ingested from Arena
Ingested 25 Jul 2026.
Price & Cost
Published API pricing by token type
USD per 1M tokens at a 3:1 input:output blend. Live from OpenRouter, cross-checked against models.dev. Lower is better.
Context Window
Maximum input tokens accepted
Maximum input context from provider metadata via models.dev and OpenRouter. Higher is better.
Speed
Median output throughput across hosting providers
Median output tokens per second across all tracked providers. Derived from OpenRouter endpoint telemetry. Higher is better.
Latency
Time to first token, median across providers
Seconds to first streamed chunk, median across tracked providers. Derived from OpenRouter endpoint telemetry. Lower is better.
Providers
Hosts serving claude-opus-4-6-thinking, with their own price and speed
No hosting providers are currently tracked for this model.
History
How price and quality have moved since we began tracking this model
Since 25 Jul 2026
| Known Good Index | — |
| Blended price | — per 1M |
| Output speed | — tok/s |
| Time to first token | — |
No recorded changes for this model since tracking began.
Comparisons
Head-to-head pages pairing claude-opus-4-6-thinking with other tracked models
Head-to-head pages are generated for the top 50 models by Known Good Index, which claude-opus-4-6-thinking is not currently in. Its nearest tracked models by index are below.