Skip to main content

DeepSeek V3

DeepSeekEstablishedReleased Dec 26, 2024
Overall Score
Est. 37Prov. #77 of 110
Arena Elo
1358
Categories Ranked
2of 8
Price (1M tokens)
$0.27 in / $1.1 out
Speed
N/A
Context
128K
Open WeightNon-Reasoning
Confidence
snapshot

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

DeepSeek V3
API / mo$1,028
Self-host / mo$18,221
Break-even1.2B/day
Model the full break-even

According to BenchLM.ai, DeepSeek V3 ranks #77 out of 110 models on the provisional leaderboard with an overall score of 37/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

DeepSeek V3 is a open weight model with a 128K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

This profile currently has 5 of 152 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Knowledge (#57), while its weakest is Instruction Following (#57). This performance profile makes it particularly effective for knowledge-intensive tasks like research, analysis, and factual Q&A.

Ranking Distribution

Category rank across 5 benchmark categories — sorted by best rank

Category Performance

Scores across all benchmark categories (0-100 scale)

Category Breakdown

Agentic

0.0/ 100
Weight: 22%0 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-VerifiedGAIATAU-benchWebArena

Coding

30.9/ 100
Weight: 20%2 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchSciCode

Reasoning

16.9/ 100
Weight: 17%0 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

#57
47.2/ 100
Weight: 12%2 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

69.9/ 100
Weight: 5%0 benchmarks
AIME 2025BRUMO 2025MATH-500FrontierMath

Multilingual

0.0/ 100
Weight: 7%0 benchmarks
MGSMMMLU-ProX

Multimodal

0.0/ 100
Weight: 12%0 benchmarks
MMMU-ProOfficeQA Pro

Inst. Following

#57
62.5/ 100
Weight: 5%1 benchmark
IFEvalIFBench

Chatbot Arena Performance

Text Overall1358CI: ±4.721,770 votes
Coding1387CI: ±10.13,280 votes
Math1311CI: ±10.72,721 votes
Instruction Following1343CI: ±6.88,606 votes
Creative Writing1349CI: ±10.03,623 votes
Multi-turn1374CI: ±9.83,747 votes
Hard Prompts1350CI: ±8.15,408 votes
Hard Prompts (English)1362CI: ±9.73,637 votes
Longer Query1374CI: ±10.63,123 votes

Benchmark Details

Only benchmark rows with an attached exact-source record are shown here. Source-unverified manual rows and generated rows are hidden from model pages.

Frequently Asked Questions

How does DeepSeek V3 perform overall in AI benchmarks?

DeepSeek V3 currently ranks #77 out of 110 models on BenchLM's provisional leaderboard with an overall score of 37 (estimated). It is created by DeepSeek and features a 128K context window.

Is DeepSeek V3 good for knowledge and understanding?

DeepSeek V3 ranks #57 out of 110 models in knowledge and understanding benchmarks with an average score of 47.2. There are stronger options in this category.

Is DeepSeek V3 good for coding and programming?

DeepSeek V3 has visible benchmark coverage in coding and programming, but BenchLM does not currently assign it a global category rank there.

Is DeepSeek V3 good for instruction following?

DeepSeek V3 ranks #57 out of 110 models in instruction following benchmarks with an average score of 62.5. There are stronger options in this category.

Is DeepSeek V3 open source?

Yes, DeepSeek V3 is an open weight model created by DeepSeek, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Does DeepSeek V3 have full benchmark coverage on BenchLM?

Not yet. DeepSeek V3 currently has 5 published benchmark scores out of the 152 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of DeepSeek V3?

DeepSeek V3 has a context window of 128K, which determines how much text it can process in a single interaction.

Last updated: April 21, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Don't miss the next GPT moment

Which models moved up, what’s new, and what it costs. One email a week, 3-min read.

Free. One email per week.