Capability
43.7/100
field median 58.1
#168 of 232 ranked models
DeepSeek V3
Released Dec 26, 2024 — see all recent releases
Decision reading
DeepSeek V3 scores 43.7 out of 100 and ranks #168 of 232. This profile shows 6 source-displayable benchmark rows; its strongest eligible category is Instruction Following at #102. API pricing is $0.27 input and $1.1 output per million tokens, with cached input at $0.07.
Data as of September 4, 2026 · How the score is built
Share or export
Strongest published evidence
Instruction Following ranks #102. A well-rounded choice across a range of tasks.
Validate before choosing
6 published rows leave some tracked benchmark slots empty. Independent runtime speed has not been measured.
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Price
$0.27input / $1.10 output
input median $1
cached $0.070 · blended $0.69
Speed
Not measured
field median 92 tok/s
Time to first token not measured
Context
128Ktokens
field median 256,000
Reported for this model; direct source link not stored
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
DeepSeek V3 category percentile values
- AgenticNot eligible
- Coding26th percentile
- ReasoningNot eligible
- Knowledge25th percentile
- MathNot eligible
- MultilingualNot eligible
- MultimodalNot eligible
- Instruction following15th percentile
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- AgenticNot ranked
- Coding#135/183
- ReasoningNot ranked
- Knowledge#136/181
- MathNot ranked
- MultilingualNot ranked
- MultimodalNot ranked
- Inst. Following#102/120
Top decileTop quartileMid-fieldNot eligible
What it costs to get this score
Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.
The chart opens on the current model. Scroll horizontally to inspect the full price axis.
Current modelDeepSeek V3 · 43.7 score · $0.69 blended per million tokens
Horizontal: blended price per million tokens, log scale · Vertical: public score
How much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- AgenticNot measured
- Coding0/2 verified
- ReasoningNot measured
- Knowledge0/2 verified
- Math1/1 verified
- MultilingualNot measured
- MultimodalNot measured
- Inst. Following0/1 verified
Verified sourceProvisionalNot measured
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 128K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Established
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Published at $0.070 per million cached input tokens
- Self-host
- DeepSeek V3 needs ~640GB VRAM (8× NVIDIA H100 (80GB)).
- Rate limits
- Not tracked yet
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
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
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticWeight 22%0 benchmarksNot measured | Not measured | Not ranked | Not available | 22% | 0 benchmarks | Not measured |
| CodingRank #135 of 183Percentile 26thWeight 20%2 benchmarksReported | 41.1 | #135 of 183 | 26th | 20% | 2 benchmarks | Reported |
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | Not ranked | Not available | 17% | 0 benchmarks | Not measured |
| KnowledgeRank #136 of 181Percentile 25thWeight 12%2 benchmarksReported | 40.7 | #136 of 181 | 25th | 12% | 2 benchmarks | Reported |
| MathRank Not rankedWeight 5%1 benchmarkVerified | 26.2 | Not ranked | Not available | 5% | 1 benchmark | Verified |
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | Not ranked | Not available | 7% | 0 benchmarks | Not measured |
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | Not ranked | Not available | 12% | 0 benchmarks | Not measured |
| Inst. FollowingRank #102 of 120Percentile 15thWeight 5%1 benchmarkReported | 39.6 | #102 of 120 | 15th | 5% | 1 benchmark | Reported |
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| LiveCodeBenchLiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code | Score37.6% | Versus best verified row Best verified: Qwen3.7 Max · 91.6% | Gap54 behind | WeightWeighted 15% | Reported |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score42% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap54 behind | WeightWeighted 10% | Reported |
Knowledge2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMLU-ProMassive Multitask Language Understanding Professional | Score75.9% | Versus best verified row Best verified: Qwen3.7 Max · 89.6% | Gap13.7 behind | WeightWeighted 20% | Reported |
| GPQAGraduate-Level Google-Proof Q&A | Score59.1% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap36.9 behind | WeightWeighted 7% | Reported |
Math1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3)FrontierMath v2 Tiers 1-3 | Score1.724% | Versus best verified row Best verified: GPT-5.6 Sol · 89.000% | Gap87.3 behind | WeightWeighted 30% | Benchmark exact |
Inst. Following1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| IFEvalInstruction-Following Eval | Score86.1% | Versus best verified row Best verified: Qwen3.5-27B · 95% | Gap8.9 behind | WeightDisplay only | Reported |
Published price history
This chart appears only when at least two dated first-party price records exist for the exact model. It shows rate changes, not an inferred cost trend.
2 dated first-party price records. The newest record lists $1.1 per million tokens.
Lineage
The sequence follows explicit supersedes links. A successor's displayed score stays at least 0.1 points above its predecessor; raw benchmark rows do not move. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Dec 26, 2024 · you are here
DeepSeek V3Score 43.7 · $0.27 / $1.1
snapshot · V3
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
DeepSeek V3 ranks #168 of 232 on the public leaderboard with a score of 43.74/100. Its source-verified position is #96 of 130.
DeepSeek V3 is a open weight model with a 128K context window. No explicit reasoning mode is documented in this profile.
6 of 422 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Instruction Following at #102, while its lowest eligible position is Knowledge at #136. a well-rounded choice across a range of tasks.
Radar
Full release historyDeepSeek V3 release history
DeepSeek V3 released
DeepSeek · Model release
Source confirmed
Radar confirmed these at the source. Already tracking DeepSeek V3? See the free Radar Brief for what changes next.
Frequently asked questions
How does DeepSeek V3 perform overall in AI benchmarks?
DeepSeek V3 ranks #168 out of 232 models on the public BenchAlign leaderboard, with a score of 43.74/100. Its evidence status is Supported, and this profile shows 6 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is DeepSeek V3 good for knowledge and understanding?
DeepSeek V3 ranks #136 out of 181 eligible models for knowledge and understanding, with a public category score of 40.7/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is DeepSeek V3 good for coding and programming?
DeepSeek V3 ranks #135 out of 183 eligible models for coding and programming, with a public category score of 41.1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is DeepSeek V3 good for mathematics?
DeepSeek V3 has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is DeepSeek V3 good for instruction following?
DeepSeek V3 ranks #102 out of 120 eligible models for instruction following, with a public category score of 39.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is DeepSeek V3 open source?
DeepSeek V3 is an open-weight model from DeepSeek. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does DeepSeek V3 have full benchmark coverage on BenchLM?
No. DeepSeek V3 currently has 22 source-displayable rows across 422 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of DeepSeek V3?
DeepSeek V3 has a reported context window of 128K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.
Compare DeepSeek V3 with every tracked model410 comparisons
Last updated September 4, 2026. Runtime fields remain blank until a sourced snapshot exists.
Watch DeepSeek V3 in the weekly brief
Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.
Read a sample issueJoin 2,000+ readers.