live
weekly refresh
basedagi.org
benchmark evidence

MATH-500

MATH-500 benchmark scores from LLM-Stats.

winner on MATH-500
direct benchmark result, not a broad vertical composite | source row dated 2000-01-01
scored on 2000-01-01 · stale source data (9646d)
latest mapped results | top 20
#ModelScoreEvidenceTested
1OpenAI: o3 Mini
Openai
97.9
model-only
independent_benchmark
2000-01-01
2OpenAI: o1
Openai
96.4
model-only
independent_benchmark
2000-01-01
3Google: Gemini 2.0 Flash
Google
89.7
model-only
independent_benchmark
2000-01-01
4OpenAI: GPT-5
Openai
84.7
model-only
independent_benchmark
2000-01-01
5Meta: Llama 3.3 70B Instruct
Meta Llama
77.0
model-only
independent_benchmark
2000-01-01
6Qwen: Qwen3 235B A22B
Qwen
71.8
model-only
independent_benchmark
2000-01-01
7Meta: Llama 4 Maverick
Meta Llama
61.2
model-only
independent_benchmark
2000-01-01
8Qwen2.5 Coder 32B Instruct
Qwen
57.2
model-only
independent_benchmark
2000-01-01
what this result means

MATH-500 benchmark scores from LLM-Stats.

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

A win here is a win on MATH-500. Broad task pages require independent corroboration before naming a general winner.

source record
category: math
metric: accuracy
matched models: 8
latest source date: 2000-01-01
direction: higher is better
inspect upstream source ->