87.4%
MMLU
Models / DeepSeek
DeepSeek R1
DeepSeek R1 · Released 2025-01-20
DeepSeek's January 2025 reasoning model. Open weights, chain-of-thought style. MATH 79.8%, strong AIME scores with extended thinking.
Self-hosted reasoning route before V4 shipped. Still relevant for reproducible CoT research and local inference stacks.
#147 of 168 on AA Index · current snapshot
20 AA Index · 16 benchmark rows · 4 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.Composite57
Context128K
Input / 1M$0.55
Output / 1M$2.2
Knowledge cutoffopen
Statuslightweight
Family profile
Best published score in each covered benchmark family.
68/100 avg
- Knowledge
- 87
- Reasoning
- 81
- Math
- 88
- Coding
- 77
- Agentic
- 16
- Long context
- 57
- Tool use
- 72
7 tested benchmark families
Benchmark placements
Per-benchmark positions
Where DeepSeek R1 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where DeepSeek R1 shows up, it's highlighted.
KnowledgeDeepSeek R1 · 87
- 191
- 291
- 391
ReasoningDeepSeek R1 · 81
- 195
- 295
- 395
MathDeepSeek R1 · 88
- 199
- 299
- 399
CodingDeepSeek R1 · 77
- 196
- 296
- 396
AgenticDeepSeek R1 · 16
- 1100
- 2100
- 3100
Long contextDeepSeek R1 · 57
- 183
- 283
- 381
Tool useDeepSeek R1 · 72
- 189
- 287
- 387
Safety
- 192
- 292
- 391
Human preference
- 195
- 292
- 391
Newest receipts
11 recentLast 120 days
Benchmark rows added to the public ledger for DeepSeek R1 in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA-LCR | Long context | 56.67% | Artificial Analysis | 5 |
| AA output speed | Performance | 0 t/s | Artificial Analysis | 5 |
| AA time to first token | Performance | 0.00s | Artificial Analysis | 5 |
| Artificial Analysis Intelligence Index | Reasoning | 20.4% | Artificial Analysis | 5 |
| GPQA Diamond | Reasoning | 81.3% | Artificial Analysis | 5 |
| Humanity's Last Exam | Reasoning | 15.8% | Artificial Analysis | 5 |
| IFBench | Reasoning | 39.59% | Artificial Analysis | 5 |
| LiveCodeBench | Coding | 77% | Artificial Analysis | 5 |
| MMLU-Pro | Knowledge | 84.9% | Artificial Analysis | 5 |
| SciCode | Coding | 40.3% | Artificial Analysis | 5 |
| Terminal-Bench | Agentic | 15.91% | Artificial Analysis | 5 |
Family coverage
Best score per family
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Price vs. performance
Where DeepSeek R1 sits on the scatter
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA
Full benchmark ledger
Every catalog benchmark for DeepSeek R1. Scores link to the original source; gaps mean no public row exists yet.
16 of 37 catalog benchmarks have a sourced row for DeepSeek R1.
Knowledge
MMLU-ProVerified
84.9%
MMLU-Pro (AA run)
Reasoning
20.4%
AA Intelligence Index v4.1
GPQA DiamondVerified
81.3%
GPQA Diamond (AA run)
Humanity's Last ExamVerified
15.8%
HLE (AA run)
IFBenchVerified
39.59%
IFBench (AA run)
64.1%
LiveBench
Math
Coding
LiveCodeBenchVerified
77%
LiveCodeBench (AA run)
SciCodeVerified
40.3%
SciCode (AA run)
Agentic
Terminal-BenchVerified
15.91%
Terminal-Bench Hard (AA run)
Long context
AA-LCRVerified
56.67%
AA-LCR (AA run)
Tool use
72.4%
BFCL
Performance
AA output speedVerified
0 t/s
Median output tokens/s (1k prompt, default provider)
AA time to first tokenVerified
0.00s
Median time to first token (1k prompt, default provider)
Sources
Where the numbers come from
- DeepSeek R1 model card· checked 2026-06-09
- DeepSeek R1 paper· checked 2026-06-09