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

CMath

A Chinese 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 CMath — September 15, 2026

We mirror the published score view for CMath. DeepSeek V4 Flash Base leads the public snapshot at 93.6%, followed by DeepSeek V4 Pro Base (90.9%). We do not use these results to rank models overall.

1Open weights

DeepSeek V4 Flash Base

DeepSeek

93.6%
Context 1M
2Open weights

DeepSeek V4 Pro Base

DeepSeek

90.9%
Context 1M

2 modelsMathCurrentDisplay onlyUpdated September 15, 2026

Benchmark score table (2 models)

Score
1
DeepSeek V4 Flash BaseDeepSeek · Open weight
93.6%
2
DeepSeek V4 Pro BaseDeepSeek · Open weight
90.9%

About CMath

Year

2026

Tasks

Chinese math problems

Format

Exact match

Difficulty

Math reasoning

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

DeepSeek-V4 Technical Report

BenchLM freshness & provenance

Version

CMath 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 CMath measure?

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

Which model scores highest on CMath?

DeepSeek V4 Flash Base by DeepSeek currently leads with a score of 93.6% on CMath.

How many models are evaluated on CMath?

2 AI models have been evaluated on CMath on BenchLM.

Last updated: September 15, 2026 · BenchLM version CMath 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.