Llama 3.1 405B Instruct
Jul 2024
Llama 3.1 405B InstructCompare inon
Benchmarks of Llama 3.1 405B Instruct4
BenchmarkByScoreRank
Legacy · saturated or no longer reported3
No benchmark matches
—per task?
price not verifiedprice
—output speed?
128Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-5.6 Lunalow×6.9—$0.01
OpenDeepSeek V4.1 Flash 1017max×10.2—$0.26Pass back reasoning_content · Chat Completions+4BetterGPT OSS 20BhighOpen×5.2—$0.011
BetterGemini 3.1 Flash Litehigh×8.2—$0.06BetterGPT-6 Lunamax×10.2—$0.068Function calling only with none · Chat Completions+3ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-5.6 Lunalow×6.9—$0.01GPT OSS 20BhighOpen×5.2—$0.011Gemini 3.1 Flash Litehigh×8.2—$0.06GPT-6 Lunamax×10.2—$0.068Function calling only with none · Chat Completions+3
Claude Haiku 5.5high×10—$0.079Remove sampling parameters+5ModelScoreCostPer taskWhat changes
DeepSeek V4.1 Flash 1017maxOpen×10.2—$0.26Pass back reasoning_content · Chat Completions+4DeepSeek V4 Pro 0813maxOpen×10.1—$0.67Pass back reasoning_content · Chat Completions+4
Kimi K3maxOpen×10—$2.00Sampling parameters are fixed+3Kimi K2.6unstatedOpen×9.9—$0.95 / $4Kimi K2.7 CodeunstatedOpen×9.8—$0.95 / $4Instant mode is not supported · Self-hosted / vLLM / SGLangModelScoreCostPer taskWhat changes
Muse Wondermax×10.2—$4 / $20Only auto tool_choice is supported+5Muse Spark 1.3xhigh×10.2—$2.15Only auto tool_choice is supported+5Muse Spark Open 816B A42B×10.1—$1.25 / $4.25Context: not verifiedMuse Sparkunstated×9.1—$1.25 / $4.25Only n=1 · Meta / Chat Completions+1Llama 4 Maverick 17B 128E Instruct FP8Open×2.1—$0.20 / $0.80Llama 4 ScoutunstatedOpen-20%—$0.10 / $0.30Llama 3.3 70B InstructunstatedOpen-47%—$0.10 / $0.32Meta Llama 3 70B InstructOpen-56%—$0.30 / $0.40Context: 128K → 8KAll Meta models →Benchmarks
all categoriesChat & Knowledge
MATH Level 549.8#21
MMLU-Pro · official boardlab73.3
GPQA Diamond · Epoch50.9#103
OTIS Mock AIME 2024 20259.7#108
Coding
SWE-bench Pro (public)11.2#18
FAQ
How much does Llama 3.1 405B Instruct cost?›
There is no per-unit API price: price not verified.
How good is Llama 3.1 405B Instruct, and what is it best at?›
#103 of 134 in Chat & Knowledge, #18 of 19 in Coding, #18 of 19 in Agents & Tool Use.
Is Llama 3.1 405B Instruct better than Phi 4?›
On OTIS Mock AIME 2024 2025, Llama 3.1 405B Instruct scores 9.7 vs 13.8 — lower.
What is the context window of Llama 3.1 405B Instruct?›
128K tokens.
When was Llama 3.1 405B Instruct released? Is there a newer version?›
Released 2024-07-23. It is the current version in its line.
What is Llama 3.1 405B Instruct?›
Llama 3.1 405B Instruct is a language model from Meta, released Jul 2024.
What are the best alternatives to Llama 3.1 405B Instruct?›
GPT-5.6 Luna (better), DeepSeek V4.1 Flash 1017 (open weights).