live
weekly refresh
basedagi.org
benchmark evidence

MathVista

MathVista: math reasoning with visual context — diagrams, charts, geometry, visual equations.

winner on MathVista
direct benchmark result, not a broad vertical composite | source row dated 2000-01-01
scored on 2000-01-01 · stale source data (9650d)
latest mapped results | top 20
#ModelScoreEvidenceTested
1OpenAI: o3
Openai
86.8
model-only
independent_benchmark
2000-01-01
2OpenAI: o4 Mini
Openai
84.3
model-only
independent_benchmark
2000-01-01
3Meta: Llama 4 Maverick
Meta Llama
73.7
model-only
independent_benchmark
2000-01-01
4OpenAI: GPT-4.1
Openai
72.2
model-only
independent_benchmark
2000-01-01
5OpenAI: o1
Openai
71.8
model-only
independent_benchmark
2000-01-01
6Meta: Llama 4 Scout
Meta Llama
70.7
model-only
independent_benchmark
2000-01-01
what this result means

MathVista: math reasoning with visual context — diagrams, charts, geometry, visual equations.

This benchmark contributes direct public evidence. Read its scope before generalizing the result.

A win here is a win on MathVista. Broad task pages require independent corroboration before naming a general winner.

source record
category: multimodal
metric: accuracy
matched models: 6
latest source date: 2000-01-01
direction: higher is better
inspect upstream source ->