Pairwise benchmark snapshot · Aug 16, 2026
This page compares Claude Opus 4.5 (Anthropic) and Claude Opus 4.6 (Anthropic) using the latest snapshots we have as of Aug 16, 2026. On preference Elo, Claude Opus 4.6 is ahead by 6 points (1,574 vs 1,568; seed-bootstrap (Aug 1, 2026)). On SWE-bench coding, Claude Opus 4.5 resolves 76.8% versus 75.9% (seed-bootstrap (Aug 1, 2026)). Claude Opus 4.6 streams faster (64 tok/s) while Claude Opus 4.5 is the cheaper output token ($25/1M). Claude Opus 4.6 has the larger context window (1M tokens). Every cell below is a dated snapshot from a named public source — we do not invent missing scores, and we do not run SWE-bench ourselves.
Anthropic
Claude Opus 4.5Anthropic frontier coding and computer-use model. SWE-bench leader on the official mini-SWE-agent harness in the Feb 2026 refresh.
Anthropic
Claude Opus 4.6Follow-on Opus release. Slightly behind 4.5 on official SWE-bench bash-only in the last published sweep; stronger long-horizon agent traces.
Instant pairwise benchmark recalculation across 400+ LLMs
Category wins across intelligence, speed, and pricing efficiency.
Preference Elo, Coding proficiency, SWE-bench & LiveBench accuracy
Generation throughput and time to first token responsiveness
Cost per million tokens and max context window length
Each spoke is a skill. Farther from the center is better (0–100th percentile). Tap any dot to inspect details.
6 pts advantage
2 tok/s faster
Same token price
Simulate monthly production API costs based on published $/1M tokens.
Higher SWE-bench (76.8%).
Lower output list price ($25/1M).
Lower TTFT (360 ms).
Larger window (1M).
Both accept images. Defaulting to the higher-Elo side (Claude Opus 4.6).
| Target Workload | Recommended Pick | Evaluation Rationale |
|---|---|---|
| Repo / coding agents | Claude Opus 4.5 | Higher SWE-bench (76.8%). |
| High-volume chat | Claude Opus 4.5 | Lower output list price ($25/1M). |
| Voice / low-latency UI | Claude Opus 4.6 | Lower TTFT (360 ms). |
| Long-document RAG | Claude Opus 4.6 | Larger window (1M). |
| Screenshots / vision | Claude Opus 4.6 | Both accept images. Defaulting to the higher-Elo side (Claude Opus 4.6). |
Slightly behind 4.5 on one official SWE-bench sweep; stronger long-horizon traces. We keep the row for old vs URLs.
The Feb refresh made 4.5 a coding reference. Newer Opus SKUs exist; this row stays as the dated harness point.
No comments posted on this matchup yet. Be the first to share an evaluation note!
The real PNG is generated at /compare/claude-opus-4-5-vs-claude-opus-4-6/opengraph-image for crawlers.
Verified head-to-head card
