The AI arena is free today

Open Superagent

Grok-2 vs Nova Pro

Grok-2 and Nova Pro are closely matched at 11.4 and 12.3 on the LLM Stats Score. Nova Pro is 2.9x cheaper per token.

xAI · Amazon · Updated for 2026

Which is better?

Grok-2 and Nova Pro are closely matched on the overall LLM Stats Score at 11.4 and 12.3.

In the 6 individual benchmarks reported for both models, Grok-2 wins 4; this is a narrower head-to-head signal than the composite indexes.

On price, Nova Pro is roughly 2.9x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Nova Pro also accepts a larger context window (300,000 input tokens), making it the stronger choice for long documents and large codebases.

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

Choose Grok-2

  • you value its reported benchmark strengths — it wins 4 of 6 exact shared results

Choose Nova Pro

  • cost matters — it's about 2.9x cheaper per token
  • you process long inputs — it offers a 300,000 token context window
  • you want the most recent training data — it shipped Nov 2024

At a glance

The differences that matter most.

Grok-2
xAI
Nova Pro
Amazon
Core performance indexes
LLM Stats Score
11.4
#258
12.3
#252
Reasoning
11.4
#255
12.0
#247
Coding
9.2
#175
10.1
#165
Cost, coverage & limits
Benchmark wins
4 of 6
2 of 6
Input price
$2.00 / M
$0.80 / M
Output price
$10.00 / M
$3.20 / M
Context window
128,000
300,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

4 shared
Index
Grok-2
Nova Pro
Math
18.2#183
18.9#172
Vision
7.4#141
5.6#150
Multimodal
10.7#114
8.4#126
Finance
18.6#93
17.3#107
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

8 reported for Grok-2 · 27 for Nova Pro

6 shared

Grok-2 outperforms in 4 benchmarks (DocVQA, GPQA, MMLU, MMMU), while Nova Pro is better at 2 benchmarks (HumanEval, MATH).

Grok-2 shows notably better performance in the majority of benchmarks.

Wed Sep 16 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Nova Pro costs less

For input processing, Grok-2 ($2.00/1M tokens) is 2.5x more expensive than Nova Pro ($0.80/1M tokens).

For output processing, Grok-2 ($10.00/1M tokens) is 3.1x more expensive than Nova Pro ($3.20/1M tokens).

In conclusion, Grok-2 is more expensive than Nova Pro.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Wed Sep 16 2026 • llm-stats.com
xAI
Grok-2
Input tokens$2.00
Output tokens$10.00
Best providerxAI
Amazon
Nova Pro
Input tokens$0.80
Output tokens$3.20
Best providerAWS Bedrock
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Nova Pro accepts 300,000 input tokens compared to Grok-2's 128,000 tokens. Nova Pro can generate longer responses up to 300,000 tokens, while Grok-2 is limited to 8,000 tokens.

xAI
Grok-2
Input128,000 tokens
Output8,000 tokens
Amazon
Nova Pro
Input300,000 tokens
Output300,000 tokens
Wed Sep 16 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Grok-2 and Nova Pro support multimodal inputs.

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

Grok-2

Text
Images
Audio
Video

Nova 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.

Grok-2

Proprietary

Closed source

Nova Pro

Proprietary

Closed source

Release Timeline

When each model was launched

Grok-2 was released on 2024-08-13, while Nova Pro was released on 2024-11-20.

Nova Pro is 3 months newer than Grok-2.

Grok-2

Aug 13, 2024

2.1 years ago

Nova Pro

Nov 20, 2024

1.8 years ago

3mo 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

Provider Availability

Grok-2 is available from xAI. Nova Pro is available from Bedrock.

Grok-2

xai logo
xAI
Input Price:Input: $2.00/1MOutput Price:Output: $10.00/1M

Nova Pro

bedrock logo
AWS Bedrock
Input Price:Input: $0.80/1MOutput Price:Output: $3.20/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

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

Grok-2
✓ Preferred
Nova Pro
Open in Playground

FAQ

Common questions about Grok-2 vs Nova Pro.

Which is better, Grok-2 or Nova Pro?

Grok-2 and Nova Pro are closely matched on the LLM Stats Score at 11.4 and 12.3. Grok-2 is made by xAI and Nova 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 Grok-2 compare to Nova Pro in benchmarks?

Grok-2 scores DocVQA: 93.6%, HumanEval: 88.4%, MMLU: 87.5%, MATH: 76.1%, MMLU-Pro: 75.5%. Nova Pro scores ARC-C: 94.8%, GSM8k: 94.8%, DocVQA: 93.5%, IFEval: 92.1%, ChartQA: 89.2%.

Is Grok-2 cheaper than Nova Pro?

Nova Pro is 2.5x cheaper for input tokens. Grok-2 costs $2.00/M input and $10.00/M output via xai. Nova Pro costs $0.80/M input and $3.20/M output via bedrock.

What are the context window sizes for Grok-2 and Nova Pro?

Grok-2 supports 128K tokens and Nova Pro supports 300K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Grok-2 and Nova Pro?

Key differences include LLM Stats Score (11.4 vs 12.3), context window (128K vs 300K), input pricing ($2.00 vs $0.80/M). See the full comparison above for benchmark-by-benchmark results.

Who makes Grok-2 and Nova Pro?

Grok-2 is developed by xAI and Nova Pro is developed by Amazon.

Related comparisons