gpt.college

DeepSeek · DeepSeek · Reviewed 2026-06-11

DeepSeek-R1

A reasoning model from DeepSeek with official benchmark results published on the DeepSeek-R1 model card.

All models
Overall · 0–100—
Status
active
Released
—
Context
Not disclosed
Parameters
Undisclosed
Inputs
Text
Type
reasoning
Max output
— tokens
API model ID
—
Reasoning
—
Knowledge cutoff
—
Training cutoff
—
Weights / license
—
Price / 1M tokens
—
Cached input
—
Strong open reasoning model positioningReported GPQA, MMLU-Pro, FRAMES, and math benchmark results
CodingReasoningResearchMultimodalAgentic

Independent benchmark scores

No snapshot score

Coding

—

No comparable score for this task lens in the selected independent snapshot.

No snapshot score

Reasoning

—

No comparable score for this task lens in the selected independent snapshot.

No snapshot score

Research

—

No comparable score for this task lens in the selected independent snapshot.

No snapshot score

Multimodal

—

No comparable score for this task lens in the selected independent snapshot.

No snapshot score

Agentic

—

No comparable score for this task lens in the selected independent snapshot.

Raw benchmark results

Source-backed rows with the original evaluation context preserved.

5 results
BenchmarkScoreSourceEvaluation notes
FRAMESChecked 2026-06-11 82.5% DeepSeek AI / Hugging Face FRAMES accuracy from the official DeepSeek-R1 model card.
GPQA / GPQA DiamondChecked 2026-06-11 71.5% DeepSeek AI / Hugging Face GPQA-Diamond Pass@1 score from the official DeepSeek-R1 model card.
Humanity's Last Exam (HLE)Checked 2026-06-12 8.54% Benchmark project Scale Labs HLE Text Only score for DeepSeek R1, covering the 86% text-only HLE subset.
MMLU-ProChecked 2026-06-11 84% DeepSeek AI / Hugging Face MMLU-Pro EM score from the official DeepSeek-R1 model card.
SWE-bench VerifiedChecked 2026-06-11 49.2% DeepSeek AI / Hugging Face SWE Verified resolved score from the official DeepSeek-R1 model card.

Strengths

  • Strong open reasoning model positioning
  • Reported GPQA, MMLU-Pro, FRAMES, and math benchmark results

Limitations

  • Hosted/API behavior and open model usage can differ by deployment

Model evidence · official · Checked 2026-06-10

DeepSeek model documentation

Use for model availability and API behavior; verify before publishing claims.

Model evidence · official · Checked 2026-06-11

DeepSeek-R1 model card

Official DeepSeek-R1 model card mirrored on Hugging Face with benchmark table for GPQA, MMLU-Pro, SWE Verified, FRAMES, and related tasks.

Task lenses preserve raw scores. Radar axes use score / current leader × 100; overall is the equal-weight average of all five indices. Missing evidence is not a zero or a low rank.