The AI arena is free today

Open Superagent

Claude 3.7 Sonnet vs Nova 2 Pro

Nova 2 Pro leads the LLM Stats Score 31.0 to 24.1.

Anthropic · Amazon · Updated for 2026

Which is better?

Nova 2 Pro leads the overall LLM Stats Score 31.0 to 24.1, ranking #107 overall.

The models split the 4 individual benchmarks reported for both models evenly.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Claude 3.7 Sonnet

  • you want predictable pricing at $3.00/M input and $15.00/M output

Choose Nova 2 Pro

  • overall performance matters — it scores 31.0 and ranks #107 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Dec 2025

At a glance

The differences that matter most.

Claude 3.7 Sonnet
Anthropic
Nova 2 Pro
Amazon
Core performance indexes
LLM Stats Score
24.1
#160
31.0
#107
Reasoning
23.2
#157
31.0
#106
Coding
14.0
#128
19.7
#97
Agents
5.0
#140
12.4
#95
Cost, coverage & limits
Benchmark wins
2 of 4
2 of 4
Input price
$3.00 / M
— / M
Output price
$15.00 / M
— / M
Context window
200,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
Claude 3.7 Sonnet
Nova 2 Pro
Math
16.7#195
26.1#99
Tool use
18.1#67
16.9#77
Writing
18.6#25
23.2#8
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

11 reported for Claude 3.7 Sonnet · 18 for Nova 2 Pro

4 shared

Claude 3.7 Sonnet outperforms in 2 benchmarks (GPQA, SWE-Bench Verified), while Nova 2 Pro is better at 2 benchmarks (AIME 2025, Terminal-Bench).

Both models are evenly matched across the benchmarks.

Fri Sep 04 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Claude 3.7 Sonnet specifies input context (200,000 tokens). Only Claude 3.7 Sonnet specifies output context (128,000 tokens).

Anthropic
Claude 3.7 Sonnet
Input200,000 tokens
Output128,000 tokens
Amazon
Nova 2 Pro
Input- tokens
Output- tokens
Fri Sep 04 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Claude 3.7 Sonnet and Nova 2 Pro support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Claude 3.7 Sonnet

Text
Images
Audio
Video

Nova 2 Pro

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

Claude 3.7 Sonnet

Proprietary

Closed source

Nova 2 Pro

Proprietary

Closed source

Release Timeline

When each model was launched

Claude 3.7 Sonnet was released on 2025-02-24, while Nova 2 Pro was released on 2025-12-02.

Nova 2 Pro is 9 months newer than Claude 3.7 Sonnet.

Claude 3.7 Sonnet

Feb 24, 2025

1.5 years ago

Nova 2 Pro

Dec 2, 2025

9 months ago

9mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Claude 3.7 Sonnet and Nova 2 Pro side-by-side, then vote on the output you prefer.

Claude 3.7 Sonnet
✓ Preferred
Nova 2 Pro
Open in Playground

FAQ

Common questions about Claude 3.7 Sonnet vs Nova 2 Pro.

Which is better, Claude 3.7 Sonnet or Nova 2 Pro?

Nova 2 Pro leads the LLM Stats Score 31.0 to 24.1. Claude 3.7 Sonnet is made by Anthropic and Nova 2 Pro is made by Amazon. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Claude 3.7 Sonnet compare to Nova 2 Pro in benchmarks?

Claude 3.7 Sonnet scores MATH-500: 96.2%, IFEval: 93.2%, MMMLU: 86.1%, GPQA: 84.8%, TAU-bench Retail: 81.2%. Nova 2 Pro scores Tau2 Telecom: 92.7%, AIME 2025: 92.3%, ScreenSpot: 88.1%, LongCodeBench: 84.0%, MMLU-Pro: 81.6%.

What are the context window sizes for Claude 3.7 Sonnet and Nova 2 Pro?

Claude 3.7 Sonnet supports 200K tokens and Nova 2 Pro supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Claude 3.7 Sonnet and Nova 2 Pro?

Key differences include LLM Stats Score (24.1 vs 31.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude 3.7 Sonnet and Nova 2 Pro?

Claude 3.7 Sonnet is developed by Anthropic and Nova 2 Pro is developed by Amazon.

Related comparisons