Home/Models/Claude Opus 5.5
C

Claude Opus 5.5

Closed API Anthropic 2026-10 1M context

The most capable closed model you can actually use — first on both long-horizon coding and professional reasoning

Intelligence v5
59.1
Leaderboard rank
#2
Input / output
$4.00/$20.00
Blended 3:1
$8.00
Output speed
94 tok/s
Value
7 pts/$
Capability profile Normalised to the field maximum
Specifications
Vendor
Anthropic
Released
2026-10
Weights
Closed, API only
Context
1,000,000 tokens
Max output
128,000 tokens
Parameters
Undisclosed
Input price
$4.00 / 1M
Output price
$20.00 / 1M
Cache hit
$0.20 / 1M
Output speed
94 tok/s
Intelligence
59.1(v5)

Benchmark scores

How it is measured →

Ranked 2 · bars are scaled to the field maximum for that benchmark.

BenchmarksScoreVs. best in fieldGap
AA Intelligence Index v5 Intelligence index 59.198% −0.9 pts
AA Intelligence Index v4.3.2 Intelligence index (legacy) 57.6100%
GPQA Diamond Graduate-level science reasoning 93.997% −2.5 pts
Terminal-Bench 4.0 Terminal-agent tasks 59.689% −7.6 pts
LiveBench Design Document generation (DOCX/PPT/PDF) 86.9100%
Vals Index Vals composite index 72.499% −0.7 pts

Assessment

Ranks first on AA Intelligence Index v5 among all publicly callable models. Fourth on Terminal-Bench 4.0 at 59.6%, behind Kimi K3.1 Pro, Gemini 4 Carbon and Sonnet 5.5, and its AA-Omniscience hallucination penalty of 46 leads Sonnet 5.5 by fourteen points. 20% cheaper than Opus 5 ($5/$25 → $4/$20).

At the same price

The four models closest on blended price, side by side.

Modelv5Blendedtok/sScore gap
Gemini 4 CarbonGoogle 60.0 $8.00 88 +0.9
Muse WonderMeta 44.0 $8.00 143 -15.1
Claude Sonnet 5.5Anthropic 54.5 $4.00 135 -4.6
GPT-6.1 SolOpenAI 54.6 $4.00 77 -4.5

Compare side by side

Line it up against other models on price, speed and every benchmark.

The comparison tool lines up to 4 models side by side with switchable normalisation — built for purchasing decisions.

Open the comparison tool → Back to leaderboard

Related benchmarks