Skip to main content
AI Choice EngineAI Choice Engine

Model comparison

Amazon Nova 2 Pro vs Claude Sonnet 5

Amazon against Anthropic, compared on context, price, and verified benchmark results.

Catalog record checked September 4, 2026Individual provider fields may changeEvidence confidence: High — see receipts below

Amazon

Amazon Nova 2 Pro

Balanced

vs

Anthropic

Claude Sonnet 5

Balanced

AI model capability comparison
SpecificationAmazon Nova 2 ProClaude Sonnet 5
ProviderAmazonAnthropic
TierBalancedBalanced
Context window1M1M
Max outputNot verifiedUnverified128K
Input / 1M tokensWinner: $1.25$2
Output / 1M tokens$10$10
WeightsClosedClosed
ParametersNot disclosedUnverifiedNot disclosedUnverified
Reasoning levelslow, medium, highadaptive
Modalitiestext, image, videotext, image
API model idamazon.nova-2-pro-preview-20251202-v1:0claude-sonnet-5
ReleasedDecember 2, 2025June 30, 2026
Artificial Analysis Intelligence Index (2026-08-14)44Winner: 55
Terminal-Bench 2.1 (2026-06-30)Not verifiedUnverified80.4
Humanity's Last Exam (2026-06-30)Not verifiedUnverified57.4
SWE-bench Verified (2026-09-01)Not verifiedUnverified79.6
LiveBench (2026-09-05)Not verifiedUnverified76

Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

  • 2026-09-05: LiveBench official leaderboard (benchmark-owned), xhigh effortContamination-resistant general capability across reasoning, coding, math, data analysis, and language, with monthly question refreshes. Comparability: comparable with caveat — Rolling question set: observations months apart measure different question mixes. Record the measurement date and compare within ~1 month windows.
  • 2026-09-01: vals.ai SWE-bench Verified leaderboard (independent, mini-swe-agent bash-only); not published by Anthropic; a 72.7 CosmicJS claim is unverifiedReal GitHub issue resolution: does the model's patch pass the hidden tests. Comparability: comparable with caveat — Post-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.
  • 2026-08-14: Artificial AnalysisComposite index blending reasoning, knowledge, and coding evals into one 0–100 score. Comparability: directly comparable — AA occasionally rebaselines the index scale between snapshots — a score captured on one date is only comparable to same-snapshot scores (check measuredAt).
  • 2026-06-30: Anthropic announcement (vendor, with tools)Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise. Comparability: comparable with caveat — Subset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.
  • 2026-06-30: Anthropic announcement table (vendor, default effort; via Vellum transcription)Agentic terminal work: multi-step tasks executed in a sandboxed shell environment. Comparability: comparable with caveat — Scores across Terminal-Bench major versions (v1 vs v2) are NOT comparable; harness configuration (container, time limits) also shifts results.

Pricing tiers: Amazon Nova 2 Pro: Standard tier $1.25/$10.00 per MTok (cross-region global endpoint, us-east-1 offer file published 2026-09-01); single-region +10%. Flex $0.625/$5.00; batch $0.69/$5.50; Priority $2.19/$17.50. Cached input ~$0.31 (secondary source). Still preview (id amazon.nova-2-pro-preview-20251202-v1:0). · Claude Sonnet 5: Standard $2/$10 per MTok; cache reads 10% of base input. Knowledge cutoff Jan 2026.

BalancedRecord checked September 4, 2026

Amazon Nova 2 Pro

Nova 2 Pro is Amazon's closed Bedrock flagship with a 1M-token context and multimodal input.

Best for

  • AWS-native workloads
  • Multimodal
  • Long-context

Watch out

Bedrock-only (closed) and still preview — pricing may change at GA. Older Nova siblings are sunsetting (Premier and original Sonic EOL 2026-09-14, Canvas/Reel 2026-09-30).

BalancedRecord checked September 3, 2026

Claude Sonnet 5

Claude Sonnet 5 is Anthropic's best speed/intelligence balance for high-volume agentic work at $2/$10.

Best for

  • Everyday generation
  • High-volume agents
  • Cost-sensitive work

Watch out

A step below Opus 5 on the hardest tasks; pick Opus when quality is paramount.

When the cheaper one wins

Both charge $10 per million output tokens at standard rates, so output price is not the split. Prefer the row whose “best for” line matches the job, then confirm the live vendor rate.

Run the model picker

Evidence confidence: High

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

  • Pricing verified on both sides — Input and output rates are verified for both models.
  • 3/5 core specs verified on both sides — Not published for at least one side: max output, parameter count.
  • 1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
  • Verified within the last 90 days — Newest catalog check was 7 days ago.
  • Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Related comparisons

Diving deeper on one model? Amazon Nova 2 Pro · Claude Sonnet 5

Common questions

Amazon Nova 2 Pro vs Claude Sonnet 5

Answered from the verified figures on this page rather than general guidance.

Is Amazon Nova 2 Pro or Claude Sonnet 5 cheaper for input?

Amazon Nova 2 Pro is cheaper at $1.25 per million input tokens, against $2 for Claude Sonnet 5 — roughly 1.6× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Amazon Nova 2 Pro has tiered pricing: Standard tier $1.25/$10.00 per MTok (cross-region global endpoint, us-east-1 offer file published 2026-09-01); single-region +10%. Flex $0.625/$5.00; batch $0.69/$5.50; Priority $2.19/$17.50. Cached input ~$0.31 (secondary source). Still preview (id amazon.nova-2-pro-preview-20251202-v1:0). Claude Sonnet 5 has tiered pricing: Standard $2/$10 per MTok; cache reads 10% of base input. Knowledge cutoff Jan 2026.

Is Amazon Nova 2 Pro or Claude Sonnet 5 cheaper for output?

Both cost $10 per million output tokens at standard rates, so output price is not a deciding factor between them.

Which has the larger context window, Amazon Nova 2 Pro or Claude Sonnet 5?

Both accept about 1M tokens of context, so document length will not decide between them.

Do Amazon Nova 2 Pro and Claude Sonnet 5 support the same reasoning levels?

Amazon Nova 2 Pro exposes low, medium, high, while Claude Sonnet 5 exposes adaptive.

Should I use Amazon Nova 2 Pro or Claude Sonnet 5?

Both sit in the balanced tier, so the choice usually comes down to price and context rather than capability. Amazon Nova 2 Pro suits aws-native workloads; Claude Sonnet 5 suits everyday generation.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

  • Input price: Amazon Nova 2 Pro costs $1.25 per 1M tokens versus $2 for Claude Sonnet 5 — a 1.6x difference at the headline tier.
  • Measured capability: Claude Sonnet 5 leads Artificial Analysis Intelligence Index 55 to 44 (measured 2026-08-14).
Run the model pickerEstimate stack costAll model comparisons

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.