Claude Sonnet 4.5 vs Llama 4 Scout

Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.

Claude Sonnet 4.5

Anthropic · Sep 2025

65.5

The model that made 30-hour autonomous coding sessions real — 77.2% SWE-bench Verified and a 1M-token context beta at $3/$15.

Llama 4 Scout

Meta · Apr 2025

A 10M-token context window — still the largest ever shipped — in a 109B MoE that fits on a single H100.

The verdict

Claude Sonnet 4.5 wins 2 of the 2 benchmarks these models share, against 0 for Llama 4 Scout. On price the gap is dramatic: Llama 4 Scout works out roughly 21x cheaper per blended million tokens. Llama 4 Scout also takes 10M of context versus 200K for Claude Sonnet 4.5. And Llama 4 Scout is open-weights (Llama 4 Community License), so it can be self-hosted — a structural advantage if data control or vendor independence matters.

Benchmark head-to-head 20

GPQA Diamond
83.4%57.2%
Claude Sonnet 4.5Llama 4 Scout
MMMU
~77.8%69.4%
Claude Sonnet 4.5Llama 4 Scout

Specs & pricing

Claude Sonnet 4.5Llama 4 Scout
modhub Index65.5
Input price / 1M$3$0.18
Output price / 1M$15$0.59
Context window200K10M
Max output64K
Open weightsnoyes (Llama 4 Community License)
Reasoning modelyesno
Multimodal inputtext, imagetext, image
Knowledge cutoffJan 2025Aug 2024
ReleasedSep 2025Apr 2025
Example monthly cost*$52.50$2.68

* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.

Frequently asked questions

Which is better, Claude Sonnet 4.5 or Llama 4 Scout?
Claude Sonnet 4.5 wins 2 of the 2 benchmarks these models share, against 0 for Llama 4 Scout. On price the gap is dramatic: Llama 4 Scout works out roughly 21x cheaper per blended million tokens. Llama 4 Scout also takes 10M of context versus 200K for Claude Sonnet 4.5. And Llama 4 Scout is open-weights (Llama 4 Community License), so it can be self-hosted — a structural advantage if data control or vendor independence matters.
Which is cheaper, Claude Sonnet 4.5 or Llama 4 Scout?
Claude Sonnet 4.5 costs $3/$15 per million input/output tokens, while Llama 4 Scout costs $0.18/$0.59. For a typical workload of 10M input and 1.5M output tokens per month, that's $52.50 versus $2.68.
Which model is better for coding, Claude Sonnet 4.5 or Llama 4 Scout?
We don't yet track SWE-bench Verified results for both models; check their individual pages for coding-related scores.

More comparisons