Claude Opus 5.5 tops the Coding Agent Index, at a higher cost per task
- Source
- Artificial Analysis
- Date
Claude Opus 5.5 is the new #1 in the Artificial Analysis Coding Agent Index, with gains across all three evaluations, though at a higher Cost per Task At max effort in Claude Code, Opus 5.5 scores 66 on the Coding Agent Index, the highest score we have measured. It is up 6 points against Opus 5 (60) and 4 points against Claude Fable 5.1 (62). Anthropic has cut Opus pricing to $4/$20 per million input/output tokens, from $5/$25 for Opus 5, and cache reads to $0.20 from $0.50. Even with those reductions, Opus 5.5’s Cost per Task is $13.04, above Opus 5’s $10.79, because it uses substantially more tokens. Key takeaways: ➤ Improves across all three Coding Agent Index evaluations: Terminal-Bench 4.0 rises to 63.1% from 54.5% for Opus 5, DeepSWE v1.1 to 68.4% from 62.5%, and SWE-Atlas-QnA to 66.4% from 62.1%. The largest gain is on Terminal-Bench, at +8.6 percentage points. ➤ The top score comes at the highest Cost per Task: Opus 5.5’s Cost per Task is $13.04, up 21% from Opus 5 at $10.79. It uses about 15.6 million tokens per task against 11.4 million for Opus 5, including about 2.4× as many output tokens. ➤ Extends the Coding Agent Index vs Cost per Task Pareto frontier: No lower-cost model in our comparison matches Opus 5.5's score. It moves the frontier upward at its high-cost end. Other model details: ➤ Pricing: $4/$20 per million input/output tokens, down 20% from Opus 5. Cache reads cost $0.20 per million, down 60% from $0.50. ➤ Evaluation setup: Claude Code at max effort, measured on DeepSWE v1.1, Terminal-Bench 4.0 and SWE-Atlas-QnA. The Coding Agent Index gives each evaluation equal weight.
Opus 5.5 costs $13.04 per Coding Agent Index task, 21% more than Opus 5 despite lower token prices. It uses 15.6 million tokens per task against 11.4 million for Opus 5, with output rising from about 137k to 333k tokens per task.
Opus 5.5 uses 15.6M tokens per task vs 11.4M for Opus 5 (+37%). Cached input rises from 10.9M to 14.6M, while output more than doubles, from 137k to 333k.
Compare Claude Opus 5.5 with other leading coding agents at: https://t.co/huXZWndXsZ
- At max effort in Claude Code, Opus 5.5 scores 66 on Artificial Analysis' Coding Index, up from 60 for Opus 5 and 62 for Claude Fable 5.1; the index weights DeepSWE v1.1, Terminal-Bench 4.0 and SWE-Atlas-QnA equally.
- Gains land on all three and are largest on Terminal-Bench 4.0 (54.5% to 63.1%); DeepSWE v1.1 rises from 62.5% to 68.4% and SWE-Atlas-QnA from 62.1% to 66.4%.
- List prices fell to $4/$20 per million input/output (from $5/$25) and cache reads to $0.20 (from $0.50), yet cost per task rose 21% to $13.04, because tokens per task grew from 11.4M to 15.6M and output from about 137k to 333k.
- No cheaper model in Artificial Analysis' comparison matches its score, so Opus 5.5 extends the index-versus-cost Pareto frontier at the high-cost end.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
- eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
Shows that Opus 5.5's coding-agent quality gains come with a 21% cost increase per task, driven by roughly 2.4x more output tokens, information needed before swapping it into cost-sensitive workflows.
Checking sign-in…
Loading comments…