DeepSeek-R1 vs GPT-4.5
Change modelsDeepSeek-R1DeepSeek
GPT-4.5OpenAI
IndexAll categories, out of 100.
38.9 ±5.0 best
38.8 ±8.9
GapIndex points below the top.
Top
−0.1 · no clear gap
CoverageIndex weight that has results.
85% best
65%
SpeedOutput tokens per second.
18/s
—
EloLMArena rating and rank.
1373
—
ReleasedMonth of release.
2025-01
2025-02
Input / 1MUS dollars per 1M input tokens.
$0.70 best
$75.00
Output / 1MUS dollars per 1M output tokens.
$2.50 best
$150.00
1K chats2K tokens in, 500 out, each.
$2.65 best
$225.00
1K documents20K tokens in, 1K out, each.
$16.50 best
$1,650.00
1K agent tasks200K tokens in, 20K out, each.
$190.00 best
$18,000.00
ContextMaximum tokens in one request.
64K
128K best
AgenticMulti-step tasks with tools.
27.6
—
CodingCode writing and repair.
42.6 best
29.1
ReasoningLogic problems and puzzles.
39.8 best
35.6
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
43.5
48.8 best
MultilingualTasks in many languages.
—
31.8
InstructionTasks with strict prompt rules.
28.5
—
MathMath problems.
43.8 best
34.0
Benchmarks
9 sharedOnly DeepSeek-R1: 25Only GPT-4.5: 3
DeepSeek-R1
GPT-4.5