Claude Sonnet 5 vs DeepSeek V4 Pro 0424: Release Comparison

Comparison of the Claude Sonnet 5 and DeepSeek V4 Pro 0424 releases: 6 and 3 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 9 models.

  • For intelligence, Claude Sonnet 5 scores highest: Claude Sonnet 5 (Adaptive Reasoning, Max Effort) at 38, against DeepSeek V4 Pro (Reasoning, Max Effort) at 31 for DeepSeek V4 Pro 0424.
  • For output speed, Claude Sonnet 5 is fastest: Claude Sonnet 5 (Adaptive Reasoning, Max Effort) at 80 t/s, against DeepSeek V4 Pro (Reasoning, Max Effort) at 74 t/s for DeepSeek V4 Pro 0424.
  • For cost per task, DeepSeek V4 Pro 0424 is cheapest: DeepSeek V4 Pro (Reasoning, Max Effort) at $0.12, against Claude Sonnet 5 (Adaptive Reasoning, Low Effort) at $0.51 for Claude Sonnet 5.

Releases compared

AnthropicClaude Sonnet 5DeepSeekDeepSeek V4 Pro 0424

Intelligence

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)

Artificial Analysis Intelligence Index v4.3 includes: 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. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Claude Sonnet 5
Pareto line

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Artificial Analysis Intelligence Index v4.3 includes: 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. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Speed & Latency

Output Speed

Output tokens per second · Higher is better

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Capability Scores

Capability Indices

Measures the performance of models on specific capabilities and industries
Finance & Accounting Index

Incorporates 5 evaluations: AA-Omniscience, GDPval-AA v2, Humanity's Last Exam, 𝜏³-Banking, AA-LCR v1.1 · Higher is better

Strategy & Ops Index

Incorporates 4 evaluations: AA-Omniscience, GDPval-AA v2, 𝜏³-Banking, AA-LCR v1.1 · Higher is better

Legal Index

Incorporates 5 evaluations: AA-Omniscience, GDPval-AA v2, AA-LCR v1.1, 𝜏³-Banking, Humanity's Last Exam · Higher is better

Healthcare & Medical Index

Incorporates 5 evaluations: AA-Omniscience, GDPval-AA v2, MLCR-AA, Humanity's Last Exam, 𝜏³-Banking · Higher is better

Engineering Index

Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, GPQA Diamond, CritPt, GDPval-AA v2, Terminal-Bench v2.1 · Higher is better

Economics Index

Incorporates 4 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2, AA-LCR v1.1 · Higher is better

Further details

Weights
Provider Benchmarks
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
Anthropic logoAnthropic
38
-
1M
$1.5
80
Not available
GoogleMicrosoft AzureAnthropicAmazon Bedrock
View
DeepSeek V4 Pro (Reasoning, Max Effort)
DeepSeek logoDeepSeek
31
1.6T
49B active at inference time
1M
$0.2
74
🤗
DeepInfraMicrosoft AzureNovita
+6
View
DeepSeek V4 Pro (Reasoning, High Effort)
DeepSeek logoDeepSeek
30
1.6T
49B active at inference time
1M
$0.2
68
🤗
DeepInfraMicrosoft AzureDeepSeek
+5
View
Claude Sonnet 5 (Non-reasoning, High Effort)
Anthropic logoAnthropic
29
-
1M
$1.5
60
Not available
AnthropicAmazon Bedrock
View
Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)
Anthropic logoAnthropic
28
-
1M
$1.5
62
Not available
Anthropic
View
Claude Sonnet 5 (Adaptive Reasoning, Low Effort)
Anthropic logoAnthropic
25
-
1M
$1.5
62
Not available
Anthropic
View
DeepSeek V4 Pro (Non-reasoning)
DeepSeek logoDeepSeek
21
1.6T
49B active at inference time
1M
$0.2
71
🤗
Microsoft AzureBitdeer AINebius
+2
View
Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)
Anthropic logoAnthropic
-
-
1M
$1.5
68
Not available
Anthropic
View
Claude Sonnet 5 (Adaptive Reasoning, High Effort)
Anthropic logoAnthropic
-
-
1M
$1.5
65
Not available
Anthropic
View