Llama 3.1 405B

Name: Llama 3.1 405B benchmark results
Creator: BenchLeader

Best configuration ranks #457 of 610 on the BenchLeader Index at 42.6 ±4.4. Last measured 2 Sept 2026. Released 23 Jul 2024.

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Benchmark	default	Source
GPQA Diamond	50.9%#198	Epoch AI Benchmarking Hub
SimpleBench	23.0%#74	SimpleBench
LMArena Hard Prompts	1341#198	LMArena
GPQA Diamond (AA)not in index	51.5%#399	Artificial Analysis
Humanity's Last Exam (AA)not in index	4.0%#469	Artificial Analysis

Benchmark	default	Source
Cybench	7.5%#18	Cybench
Terminal-Bench Hard	6.8%#240	Artificial Analysis
τ²-Bench Telecom (AA)not in index	19.0%#329	Artificial Analysis

Benchmark	default	Source
OTIS Mock AIME	9.7%#210	Epoch AI Benchmarking Hub
MATH Level 5	49.8%#53	Epoch AI Benchmarking Hub

Benchmark	default	Source
AA-Omniscience	-17.1#170	Artificial Analysis

Benchmark	default	Source
IFBench	39.0%#262	Artificial Analysis

Benchmark	default	Source
LMArena Text	1335#198	LMArena

Benchmark	default	Source
AA-LCR	25.3%#339	Artificial Analysis

Benchmark	default	Source
Epoch Capabilities Indexnot in index	128.8#138	Epoch AI Benchmarking Hub
AA Intelligence Index	7.3#405	Artificial Analysis