LAMBADA

Models scored

53

Best score

0.87

Metric

Score

LAMBADA is an AI evaluation tracked by Epoch AI, with 53 scored model versions on record. The scores here are reported by third parties rather than produced by Epoch AI running the evaluation itself.

Scored models span December 2021 to November 2023. The best score recorded is 0.87, measured as Score. Models come from MosaicML, Baichuan, Meta AI, Stability AI, Alibaba, OpenAI, DeepMind, Microsoft,NVIDIA and others.

Full record

Score metric: Score
Models scored: 53
Best score recorded: 0.87
Earliest model scored: Dec 8, 2021
Most recent model scored: Nov 30, 2023
Third-party reported: Yes

Leaderboard

01	Megatron-Turing NLG 530B	Microsoft,NVIDIA	0.87
02	text-davinci-001	OpenAI	0.86
03	falcon-180B	Technology Innovation Institute	0.8
04	Llama-2-70b-hf	Meta AI	0.79
05	Inflection-1	Inflection AI	0.79
06	PaLM 540B	Google Research	0.78
07	LLaMA-65B	Meta AI	0.78
08	Chinchilla (70B)	DeepMind	0.77
09	falcon-40b	Technology Innovation Institute	0.77
10	LLaMA-33B	Meta AI	0.77
11	Llama-2-13b	Meta AI	0.77
12	LLaMA-13B	Meta AI	0.75
13	falcon-7b	Technology Innovation Institute	0.75
14	Gopher (280B)	DeepMind	0.74
15	Baichuan-2-13B-Base	Baichuan	0.74
16	Baichuan-2-7B-Base	Baichuan	0.73
17	LLaMA-7B	Meta AI	0.73
18	Llama-2-7b	Meta AI	0.73
19	internlm-20b		0.72
20	StableBeluga2	Stability AI	0.71
21	Qwen-14B	Alibaba	0.71
22	mpt-7b	MosaicML	0.7
23	Qwen-7B	Alibaba	0.68
24	internlm-7b		0.67
25	Qwen-1_8B		0.58
26	chatglm2-6b		0.54

More benchmarks

Epoch Capabilities Index MMLU Terminal-Bench GPQA Diamond OTIS Mock AIME 2024-2025 GSM8K ARC-AGI ARC-AGI-2

SourceEpoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/benchmarks. Licensed under CC BY 4.0.

← All benchmarks