Compare
Llama 4 Behemoth vs GPT-5 Turbo
Meta vs OpenAI. Specs, benchmarks, and real per-task cost — all in one page.
Verdict
GPT-5 Turbo leads on LMSYS ELO (1398 vs 1342). Llama 4 Behemoth is ~2.7× cheaper on a 3:1 input:output blend. Llama 4 Behemoth is open-weights, the other is proprietary.
Meta
Llama 4 BehemothMeta’s open-weights flagship. 405B params, fully open license, runs on every major inference provider.
Best open-weights modelRuns anywhereTransparent training
OpenAI
GPT-5 TurboOpenAI’s flagship unified model. Handles text, vision, and audio natively. The generalist benchmark champion.
Native multimodalStrong math and scienceHuge ecosystem
Pricing
Input / 1M$2.50$6.00
Output / 1M$8.00$24.00
Context256K400K
Max output16K32K
LicenseOpen weightsProprietary
Released2025-12-102026-01-21
Benchmarks
LMSYS ELO1342.01398.0
MMLU Pro87.191.2
HumanEval89.393.0
SWE-Bench52.465.8
MATH81.591.5
GPQA56.268.1
MMMU—78.8
IFEval88.088.9
Per-task cost
Summarize a 1-hour meeting transcript$0.041$0.102
Review a 500-line pull request$0.036$0.096
Answer a customer support ticket$0.014$0.037
Extract structured data from a resume$0.021$0.054
Debug a stack trace with context$0.031$0.084
Per-call cost using published token counts for each task. Real-world prompts vary.