Compare

Llama 4 Scout vs Gemini 2.5 Flash

Meta vs Google DeepMind. Specs, benchmarks, and real per-task cost — all in one page.

Verdict

Gemini 2.5 Flash leads on LMSYS ELO (1312 vs 1265). Llama 4 Scout is ~1.1× cheaper on a 3:1 input:output blend. Llama 4 Scout is open-weights, the other is proprietary.

Meta

Llama 4 Scout

The 70B workhorse open-weight. Fits on a single H100, beloved by self-hosters.

Single-GPU deployableDirt cheap on aggregatorsStrong fine-tuning base

Google DeepMind

Gemini 2.5 Flash

Google’s price/performance darling. 1M context at $0.30/M input — nobody comes close on throughput-per-dollar.

Absurd cost-to-context ratioFast multimodalFree tier via AI Studio

Pricing

Input / 1M$0.35$0.30

Output / 1M$0.80$1.20

Context128K1.0M

Max output8K32K

LicenseOpen weightsProprietary

Released2025-12-102026-02-05

Benchmarks

LMSYS ELO1265.01312.0

MMLU Pro77.282.1

HumanEval82.485.8

MATH72.584.2

MMMU—74.6

IFEval84.186.1

Per-task cost

Summarize a 1-hour meeting transcript$0.0057$0.0051

Review a 500-line pull request$0.0044$0.0048

Answer a customer support ticket$0.0017$0.0019

Extract structured data from a resume$0.0026$0.0027

Debug a stack trace with context$0.0037$0.0042

Per-call cost using published token counts for each task. Real-world prompts vary.

Tool

Interactive compare →

Add up to four models, tweak tasks live.