Brain-Score - Tuckute2024-ridge_pearsonr

Leaderboard Explore Compare Profile Community Blog FAQ Competition 2024 Report Issue

Sample stimuli

sample 0

sample 1

sample 2

sample 3

sample 4

sample 5

sample 6

sample 7

sample 8

sample 9

How to use

from brainscore_language import load_benchmark
benchmark = load_benchmark("Tuckute2024-ridge_pearsonr")
score = benchmark(my_model)

Model scores

Score Legend Min Alignment Max Alignment

Rank	Model	Score
1	mistral-7b
2	openai-gpt
3	tinyllama-1.1b
4	qwen3-8b-loc-10
5	qwen3-4b-loc-10
6	glove-840b
7	qwen3-14b-loc-10
8	pythia-12b
9	falcon-7b
10	pythia-2.8b
11	qwen3-1.7b-loc-10
12	gpt2-xl
13	qwen3-0.6b-loc-10
14	phi-2
15	gpt-neo-2.7B
16	gpt-neo-1.3B
17	opt-6.7b
18	gpt2
19	opt-2.7b
20	gpt2-medium
21	gpt2-large
22	qwen2.5-14b
23	distilgpt2
24	test_embedding_4
25	qwen2.5-3b
26	randomembedding-100
27	gpt-neo-125m
28	randomembedding-1600
29	oasm-sigma0.6
30	oasm-sigma0.5
31	oasm-sigma0.4
32	oasm-sigma0.3
33	oasm-sigma0
34	lm1b

Benchmark bibtex

None

Ceiling

Not available

Data: Tuckute2024

Metric: ridge_pearsonr