Compare/Claude Sonnet 5 (Adaptive Reasoning, Max Effort) vs Nova 2.0 Pro Preview (medium)

Claude Sonnet 5 (Adaptive Reasoning, Max Effort)vsNova 2.0 Pro Preview (medium)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Anthropic

Claude Sonnet 5 (Adaptive Reasoning, Max Effort)

Input
$2/M
Output
$10/M
Speed
87 tok/s
TTFT
134.45s
Amazon

Nova 2.0 Pro Preview (medium)

Input
$1.25/M
Output
$10/M
Speed
125 tok/s
TTFT
16.13s

Winner by Category

Cheaper
Nova 2.0 Pro Preview (medium)
Faster (tok/s)
Nova 2.0 Pro Preview (medium)
Lower Latency
Nova 2.0 Pro Preview (medium)
Benchmarks (5-6)
Nova 2.0 Pro Preview (medium)

Pricing Comparison

MetricClaude Sonnet 5 (Adaptive Reasoning, Max Effort)Nova 2.0 Pro Preview (medium)
Input ($/M tokens)$2$1.25
Output ($/M tokens)$10$10
Cost for 1M input + 100K output tokens:
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)$3.00
Nova 2.0 Pro Preview (medium)$2.25

Speed Comparison

Output Speed (tokens/s) — higher is better
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
87 tok/s
Nova 2.0 Pro Preview (medium)
125 tok/s
Time to First Token (seconds) — lower is better
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
134.45s
Nova 2.0 Pro Preview (medium)
16.13s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
53.421.8
Coding Index
71.534.0
Math Index
89.0
GPQA Diamond
91.1%78.5%
MMLU-Pro
83.0%
LiveCodeBench
73.0%
AIME 2025
89.0%
MATH-500
Humanity's Last Exam
39.6%8.9%
SciCode
53.6%42.7%
IFBench
79.0%
TerminalBench
24.2%
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)5 wins
6 winsNova 2.0 Pro Preview (medium)

Frequently Asked Questions

Which is cheaper, Claude Sonnet 5 (Adaptive Reasoning, Max Effort) or Nova 2.0 Pro Preview (medium)?

Nova 2.0 Pro Preview (medium) is cheaper overall. Its blended price (3:1 input/output ratio) is $3.44/M tokens vs $4.00/M for Claude Sonnet 5 (Adaptive Reasoning, Max Effort).

Which model performs better on benchmarks?

Nova 2.0 Pro Preview (medium) wins 6 out of 12 benchmarks compared to 5 for Claude Sonnet 5 (Adaptive Reasoning, Max Effort). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Nova 2.0 Pro Preview (medium) generates tokens faster at 125 tok/s vs 87 tok/s. However, Nova 2.0 Pro Preview (medium) has lower time-to-first-token (16.13s vs 134.45s).

When should I use Claude Sonnet 5 (Adaptive Reasoning, Max Effort) vs Nova 2.0 Pro Preview (medium)?

Choose based on your priorities: Nova 2.0 Pro Preview (medium) for lower cost, Nova 2.0 Pro Preview (medium) for stronger benchmark performance, and Nova 2.0 Pro Preview (medium) for faster generation. For latency-sensitive apps, check the TTFT comparison above.