Leaderboard Benchmarks Methodology Status

every LLM benchmark, one honest table

Leaderboard / deepseek

DeepSeek V4.1 Flash

DeepSeekopen weights

DeepSeek V4.1 Flash model for reasoning and agentic coding

Benchmarks

No aggregated scores for this model yet.

Specs

Context window: 1M
Max output: 384K
Knowledge cutoff: 2025-05
Released: Sep 10, 2026
Weights: Open
Reasoning: Yes
Input modalities: text, image

Pricing / 1M tokens

deepseek: $0.15 in · $0.6 out

llm.ing

Aggregated LLM benchmarks, prices, and specs with per-score provenance. No bot walls — this site is meant to be read by humans and machines alike.

JSON API · llms.txt

Data sources

models.dev — model registry & pricing (MIT)
OpenRouter — live pricing & provider stats
LMArena — crowd Elo (CC BY 4.0)
Artificial Analysis — intelligence, coding & agentic indices

Attribution

Benchmark indices include data from Artificial Analysis. Arena ratings © LMArena, CC BY 4.0. Registry data via models.dev contributors.

Scores link to their origin. See methodology.