Anthropic:モデルの知能、性能、料金

Anthropic
Anthropic

この分析は、ユースケースに最適なAnthropic提供モデルを選ぶための参考情報です。

最高の知能

Updated
#1
Claude Fable 5.1 (max with fallback)Claude Fable 5.1 (max with fallback)
53
#2
Claude Fable 5.1 (xhigh with fallback)Claude Fable 5.1 (xhigh with fallback)
53
#3
Claude Fable 5.1 (high with fallback)Claude Fable 5.1 (high with fallback)
51
#4
Claude Opus 5 (max)Claude Opus 5 (max)
51
#5
Claude Fable 5 (with fallback)Claude Fable 5 (with fallback)
50

Intelligence Index

モデル合計:31件

最速

#1
Claude Sonnet 5 (max)Claude Sonnet 5 (max)
84 t/s
#2
Claude 4.5 HaikuClaude 4.5 Haiku
83 t/s
#3
Claude 4.5 Haiku (Non-reasoning)Claude 4.5 Haiku (Non-reasoning)
79 t/s
#4
Claude Sonnet 5 (xhigh)Claude Sonnet 5 (xhigh)
66 t/s
#5
Claude Fable 5.1 (max with fallback)Claude Fable 5.1 (max with fallback)
65 t/s

出力速度

モデル合計:31件

最安料金

#1
Claude 4.5 HaikuClaude 4.5 Haiku
$0.77
#2
Claude 4.5 Haiku (Non-reasoning)Claude 4.5 Haiku (Non-reasoning)
$0.77
#3
Claude Sonnet 5 (max)Claude Sonnet 5 (max)
$1.54
#4
Claude Sonnet 5 (xhigh)Claude Sonnet 5 (xhigh)
$1.54
#5
Claude Sonnet 5 (high)Claude Sonnet 5 (high)
$1.54

ブレンド料金(100万トークンあたり)

モデル合計:31件

Anthropicは31モデルを提供しており、知能、性能、料金の特性はそれぞれ異なります。 以下でモデル間の主要指標を比較します。

  • Anthropicで知能が上位のモデルはClaude Fable 5.1 (max with fallback)(53)、Claude Fable 5.1 (xhigh with fallback)(53)、Claude Fable 5.1 (high with fallback)(51)です。
  • 出力速度が最も速いモデルはClaude Sonnet 5 (max)(84 t/s)、Claude 4.5 Haiku(83 t/s)、Claude 4.5 Haiku (Non-reasoning)(79 t/s)です。
  • 遅延では、Claude Sonnet 5 (Non-reasoning)(0.68秒)、Claude 4.5 Haiku (Non-reasoning)(0.73秒)、Claude Opus 4.7 (Non-reasoning, high)(0.92秒)の最初の回答トークンまでの時間が最短です。
  • 料金では、Claude 4.5 Haiku($0.77)、Claude 4.5 Haiku (Non-reasoning)($0.77)、Claude Sonnet 5 (max)($1.54)の100万トークンあたりのブレンド料金が最安です。
  • Anthropicで最大のコンテキストウィンドウに対応するモデルはClaude Fable 5.1 (max with fallback)(1M)、Claude Fable 5.1 (xhigh with fallback)(1M)、Claude Fable 5.1 (high with fallback)(1M)です。

ハイライト

Updated
Artificial Analysis Intelligence Index · Higher is better
Output tokens per second · Higher is better
USD per 1M tokens (blended) · Lower is better

知能評価

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench v4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1
Estimate (independent evaluation forthcoming)

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
See more

Agentic knowledge work, (Elo-500)/2000

Agentic real-world work tasks, (Elo-500)/2000

Agentic SaaS workflows

Agentic coding & terminal use

Coding

Reasoning & knowledge

Professional document reasoning, All-pass

Physics reasoning

Long context reasoning

Legal agentic work, criterion pass rate

Agentic business operations

Quantitative analysis on spreadsheets & documents

Instruction following

Agentic tool use

Long-horizon agentic tasks

No data available

Kubernetes incident root-cause analysis

Visual reasoning

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

コンテキストウィンドウ

Context Window

Context window: tokens limit · Higher is better

料金

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

性能の概要

Output Speed vs. Price

Output speed: output tokens per second · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

速度

出力速度(1秒あたりのトークン数)で測定

Output Speed

Output tokens per second · Higher is better

遅延

最初のトークンまでの時間(秒)で測定

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time

エンドツーエンド応答時間

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time vs. Price

End-to-end response time: end-to-end seconds to output 500 tokens · USD per 1M tokens (blended)
Most attractive quadrant

詳細分析
Anthropicのロゴ
Claude Fable 5.1 (max with fallback)
1M
独自
53
$7.63
65
210.79
218.47
--
Anthropicのロゴ
Claude Fable 5.1 (xhigh with fallback)
1M
独自
53
$5.98
60
88.63
97.01
--
Anthropicのロゴ
Claude Fable 5.1 (high with fallback)
1M
独自
51
$3.91
55
14.87
23.98
--
Anthropicのロゴ
Claude Opus 5 (max)
1M
独自
51
$5.86
52
48.08
57.75
--
Anthropicのロゴ
Claude Fable 5 (with fallback)
1M
独自
50
$8.75
61
88.23
96.48
--
Anthropicのロゴ
Claude Opus 5 (xhigh)
1M
独自
50
$4.88
53
26.77
36.19
--
Anthropicのロゴ
Claude Fable 5.1 (medium with fallback)
1M
独自
49
$2.98
54
8.69
18.01
--
Anthropicのロゴ
Claude Opus 5 (high)
1M
独自
48
$3.61
51
11.51
21.34
--
Anthropicのロゴ
Claude Fable 5.1 (low with fallback)
1M
独自
47
$2.37
53
4.71
14.15
--
Anthropicのロゴ
Claude Opus 5 (medium)
1M
独自
45
$2.19
51
3.65
13.41
--
Anthropicのロゴ
Claude Opus 4.8 (max)
1M
独自
42
$4.08
56
21.59
30.50
--
Anthropicのロゴ
Claude Opus 4.7 (max)
1M
独自
41*
--
47
17.93
28.54
--
Anthropicのロゴ
Claude Opus 5 (low)
1M
独自
40
$1.10
53
2.71
12.14
--
Anthropicのロゴ
Claude Sonnet 5 (max)
1M
独自
38
$5.09
84
209.43
215.39
--
Anthropicのロゴ
Claude Sonnet 5 (xhigh)
1M
独自
35
$2.87
66
24.85
32.45
--
Anthropicのロゴ
Claude Sonnet 5 (high)
1M
独自
32
$1.79
61
2.30
10.53
--
Anthropicのロゴ
Claude Opus 4.6 (max)
1M
独自
32*
--
39
15.55
28.30
--
Anthropicのロゴ
Claude Opus 4.7 (Non-reasoning, high)
1M
独自
31*
--
45
0.92
12.16
--
Anthropicのロゴ
Claude Sonnet 4.6 (max)
1M
独自
30
$2.49
56
139.00
147.91
--
Anthropicのロゴ
Claude Opus 4.5
200k
独自
29*
--
44
10.85
22.22
--
Anthropicのロゴ
Claude Sonnet 5 (Non-reasoning)
1M
独自
29*
--
61
0.68
8.82
--
Anthropicのロゴ
Claude Sonnet 5 (medium)
1M
独自
28
$1.00
59
1.25
9.72
--
Anthropicのロゴ
Claude Opus 4.6 (Non-reasoning, high)
1M
独自
26*
--
38
1.93
15.06
--
Anthropicのロゴ
Claude Sonnet 5 (low)
1M
独自
25
$0.51
57
0.98
9.81
--
Anthropicのロゴ
Claude Sonnet 4.6 (Non-reasoning, high)
1M
独自
25*
--
43
1.52
13.21
--
Anthropicのロゴ
Claude Opus 4.5 (Non-reasoning)
200k
独自
24*
--
44
1.25
12.62
--
Anthropicのロゴ
Claude Sonnet 4.6 (Non-reasoning, low)
1M
独自
23*
--
42
1.33
13.18
--
Anthropicのロゴ
Claude 4.1 Opus
200k
独自
23*
--
--
--
--
--
Anthropicのロゴ
Claude 4.5 Sonnet
1M
独自
21
$0.56
41
9.44
21.48
--
Anthropicのロゴ
Claude 4 Opus
200k
独自
21*
--
--
--
--
--
Anthropicのロゴ
Claude 4.5 Sonnet (Non-reasoning)
1M
独自
19*
--
40
1.30
13.77
--
Anthropicのロゴ
Claude 4 Sonnet
1M
独自
19*
--
--
--
--
--
Anthropicのロゴ
Claude 4.1 Opus (Non-reasoning)
200k
独自
19*
--
--
--
--
--
Anthropicのロゴ
Claude 4.5 Haiku
200k
独自
18
$0.21
83
13.35
19.40
--
Anthropicのロゴ
Claude 4 Opus (Non-reasoning)
200k
独自
17*
--
--
--
--
--
Anthropicのロゴ
Claude 4 Sonnet (Non-reasoning)
1M
独自
17*
--
--
--
--
--
Anthropicのロゴ
Claude 4.5 Haiku (Non-reasoning)
200k
独自
15*
--
79
0.73
7.06
--
Anthropicのロゴ
Claude 3 Opus
200k
独自
9*
--
--
--
--
--

主要な定義

よくある質問

Anthropicに関するよくある質問