Skip to main content

Claude Sonnet 5 (Non-reasoning, High Effort)

AnthropicClaude
Release Date
2026-06-30
Parameters
—
Context Length
1.0M
Modalities
image, pdf, text

Capability Radar

22
general
66
coding
80
reasoning
61
science
76
agents
80
multimodal

Rankings

Domain#RankScoreSource
Code Ranking120
80.0
AA
General Ranking361
37.0
AA
Math Reasoning20
93.0
LB
Reasoning18
89.0
LB
Science225
56.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

No benchmark data available

AA Evaluation Indices

(Artificial Analysis)
Gpqa(NYU + Cohere + Anthropic (2023))
80.0
Terminalbench V2 1
75.3
Lcr(Artificial Analysis)
70.0
Coding Index(Artificial Analysis)
66.4
Intelligence Index(Artificial Analysis)
23.2
Hle(Center for AI Safety + Scale AI (2025))
19.0
Tau Banking
15.7

LLM Stats Category Scores

(LLM Stats (zeroeval))

No category score data available

Pricing

Input Price$2 / 1M tokens
Output Price$10 / 1M tokens
Blended Price (3:1)$4 / 1M tokens
Cache Read Price$0.2 / 1M tokens
Cache Write Price$2.5 / 1M tokens

Speed

Tokens/sec70.4
Time to First Token0.97s
Time to Answer0.97s

Provider Price Ranking

Provider Price Ranking

17 providers

Cheapest: UnoRouterMost Expensive: Venice AI
ProviderInputOutput
1UnoRouterCheapest
$1.44
$7.2
2AnthropicPRIMARY
$2
$10
3302.AI
$2
$10
4Vivgrid
$2
$10
5GitHub Copilot
$2
$10
6OpenCode Zen
$2
$10
7AIHubMix
$2
$10
8Azure Cognitive Services
$2
$10
9Requesty
$2
$10
10DevPass (LLM Gateway)
$2
$10
11Azure
$2
$10
12Neon
$2
$10
13Pioneer
$2
$10
14Cortecs
$2.2
$11
15Opper
$2.2
$11
16Abacus
$3
$15
17Venice AI
$3
$15

Compare pricing across different API providers for this model.

External Sources