Skip to main content
Launching the open-source gateway

Claude Opus 4 vs DeepSeek R1 0528

SpecClaude Opus 4DeepSeek R1 0528
Respan Index21.9 (#110)21.0 (#111)
Blended price per 1M-$0.912
Context window200K-
Input / output per 1M-$0.5 / $2.15
Max output32K66K
Inputtext, visiontext
Released2025-05-222025-05-28

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.

CategoryClaude Opus 4DeepSeek R1 0528
Coding8.4 Claude Opus 45.3 DeepSeek R1 0528
Agents20.7* Claude Opus 418.9* DeepSeek R1 0528
Reasoning22.7 Claude Opus 423.1 DeepSeek R1 0528
Knowledge & language18.0* Claude Opus 419.6 DeepSeek R1 0528
Human preference47.4 Claude Opus 448.0 DeepSeek R1 0528

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

Benchmarks both report

Claude Opus 4 leads on 4 of the 7 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkClaude Opus 4DeepSeek R1 0528
LMArena Elo14261422
GPQA Diamond76.3%81%
MATH Level 5 (Epoch AI)85%96.6%
OTIS Mock AIME 2024-2025 (Epoch AI)64.4%66.4%
SimpleBench (SimpleBench)58.8%40.8%
WeirdML (Håvard Tveit Ihle)43.7%41.6%
SWE-bench Verified72.5%57.6%

FAQ

Is Claude Opus 4 better than DeepSeek R1 0528?

Claude Opus 4 scores 21.9 on the Respan Index (#110), ahead of DeepSeek R1 0528 at 21.0 (#111). Claude Opus 4 leads on 4 of the 7 benchmarks both report.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.