Skip to main content
Launching the open-source gateway

DeepSeek R1 vs o3-mini

SpecDeepSeek R1o3-mini
Respan Index18.1 (#132)17.8 (#133)
Blended price per 1M$1.15$1.93
Context window128K200K
Input / output per 1M$0.7 / $2.5$1.1 / $4.4
Max output33K100K
Inputtexttext
Released2025-01-202025-01-31

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryDeepSeek R1o3-mini
Coding3.9 DeepSeek R14.5 o3-mini
Agents14.4 DeepSeek R114.2* o3-mini
Reasoning20.4 DeepSeek R122.4 o3-mini
Knowledge & language16.7 DeepSeek R115.3 o3-mini
Human preference44.7 DeepSeek R140.3 o3-mini

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

o3-mini leads on 5 of the 8 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkDeepSeek R1o3-mini
GPQA Diamond71.5%74.9%
MATH Level 5 (Epoch AI)93.1%96.5%
OTIS Mock AIME 2024-2025 (Epoch AI)53.3%76.9%
WeirdML (Håvard Tveit Ihle)36.5%43.7%
LMArena Elo13981364
SimpleBench (SimpleBench)30.9%22.8%
AIME 202570%86.7%
MMLU90.8%85.9%

FAQ

Is DeepSeek R1 better than o3-mini?

DeepSeek R1 scores 18.1 on the Respan Index (#132), ahead of o3-mini at 17.8 (#133). o3-mini leads on 5 of the 8 benchmarks both report.

Which is cheaper, DeepSeek R1 or o3-mini?

DeepSeek R1 lists at $0.7 input and $2.5 output per 1M tokens; o3-mini at $1.1 and $4.4. DeepSeek R1 is 1.7x cheaper per token at list price.

Which has the larger context window?

DeepSeek R1 accepts 128K tokens and o3-mini 200K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.