GPT-4.1 vs DeepSeek R1 0528

It is close. Our weighted score puts them within a point (DeepSeek R1 0528 53/100, GPT-4.1 52/100), so choose by what matters most for your work: DeepSeek R1 0528 for raw capability and GPT-4.1 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

DeepSeek R1 0528 is cheaper at $0.512 input / $2.19 output per million tokens (median across 16 API providers). GPT-4.1 costs $2.00 input / $8.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $0.932 per million tokens for DeepSeek R1 0528 versus $3.50 for GPT-4.1 (3.8× as much).

DeepSeek R1 0528 scores higher on the Capabilities Index (ECI): DeepSeek R1 0528 141.2 (#108 of 165) and GPT-4.1 136.7 (#125 of 165). Their confidence ranges do not overlap (139.0–142.9 vs 134.0–138.5), so the gap is a real one. On individual benchmarks: GPQA Diamond — DeepSeek R1 0528 76.3%, GPT-4.1 66.9%; OTIS Mock AIME 2024–2025 — DeepSeek R1 0528 66.4%, GPT-4.1 38.3%.

There are no published SWE-bench Verified results for DeepSeek R1 0528 yet, so there is no like-for-like coding score. On overall capability, DeepSeek R1 0528 leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

GPT-4.1 has the largest context window at 1,047,576 tokens, against 163,840 for DeepSeek R1 0528. Maximum output per response: GPT-4.1 up to 32,768, DeepSeek R1 0528 up to 32,768 tokens.

GPT-4.1 accepts text, images and PDFs; DeepSeek R1 0528 accepts text. GPT-4.1 handles the widest range of inputs.

DeepSeek R1 0528 publishes its weights (MIT) and can be self-hosted; GPT-4.1 is proprietary.

DeepSeek R1 0528 is the newest, released May 28, 2025. GPT-4.1 came out Apr 14, 2025. Knowledge cutoff: GPT-4.1 Apr 2024.

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.