Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

MATH

A competition-style mathematical reasoning benchmark reported in DeepSeek-V4 base-model evaluations.

Data verified 33 confirmed releases in the last 30 daysSee provider release alerts

Benchmark score on MATH — September 15, 2026

We mirror the published score view for MATH. DeepSeek V4 Pro Base leads the public snapshot at 64.5%, followed by DeepSeek V4 Flash Base (57.4%). We do not use these results to rank models overall.

1Open weights

DeepSeek V4 Pro Base

DeepSeek

64.5%
Context 1M
2Open weights

DeepSeek V4 Flash Base

DeepSeek

57.4%
Context 1M

2 modelsMathCurrentDisplay onlyUpdated September 15, 2026

Benchmark score table (2 models)

Score
1
DeepSeek V4 Pro BaseDeepSeek · Open weight
64.5%
2
DeepSeek V4 Flash BaseDeepSeek · Open weight
57.4%

About MATH

Year

2026

Tasks

Competition math problems

Format

Exact match

Difficulty

Advanced math reasoning

BenchLM stores MATH as a display-only provider-table row when exact values are published in DeepSeek-V4 evaluations.

DeepSeek-V4 Technical Report

BenchLM freshness & provenance

Version

MATH 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does MATH measure?

A competition-style mathematical reasoning benchmark reported in DeepSeek-V4 base-model evaluations.

Which model scores highest on MATH?

DeepSeek V4 Pro Base by DeepSeek currently leads with a score of 64.5% on MATH.

How many models are evaluated on MATH?

2 AI models have been evaluated on MATH on BenchLM.

Last updated: September 15, 2026 · BenchLM version MATH 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.