LuminaBench
DeepSeek / Published benchmarks

DeepSeek-V4.1-Flash-1017 (Max, DSH)

Benchmark results and API pricing.

Best recorded results

Benchmark scores

Best eligible score in each benchmark.

API pricing

USD / 1M tokens

Verified pricing is unavailable for this model.

ArXivMath — September 2026

ArXivMath — September 2026

Version MathArena-arxiv--september-20261106
Lumina VerifiedLumina checked the published sources, versions, model labels, score extraction and conversion. External evaluations were run by their publishers; Lumina has not independently rerun or reproduced them.

1 configuration · Publisher-run · Experimental conversion

949Best score · Not specified
Explore ArXivMath — September 2026
BrokenArXiv — September 2026

BrokenArXiv — September 2026

Version MathArena-arxiv_false--september-20261106
Lumina VerifiedLumina checked the published sources, versions, model labels, score extraction and conversion. External evaluations were run by their publishers; Lumina has not independently rerun or reproduced them.

1 configuration · Publisher-run · Experimental conversion

1,002Best score · Not specified
Explore BrokenArXiv — September 2026