The Open-Source AI Stack
RSS
All models

Models · o-series

OpenAI o3

Proprietary OpenAI · 2025-04-16 · Proprietary

Released April 16, 2025 as the full-size successor to o1 in the o-series reasoning lineage, with multimodal (text plus image) input and a 200K-token context. OpenAI reported large jumps over o1 on SWE-bench Verified and Codeforces and roughly 3x the accuracy of o1 on ARC-AGI.

Cost

$2.00 / Mtok input
$8.00 / Mtok output

OpenAI API · as of 2026-05-21

source ↗

Speed

88 tok/sec output
10746 ms TTFT

· as of 2026-05-21

source ↗

Architecture

tokens in Embedding vocab not disclosed × N layers Architecture not disclosed (proprietary or undocumented) Output projection tokens out
Schema-generated from data/models.yaml. Every label is auditable against the model's sources.

Specs

Architecture
unknown
Total params
not disclosed
Active params
not disclosed
Context window
200K tokens
Attention
unknown
Position encoding
unknown
Post-training
rlhf
OSI-approved
no
Data released
no
Training code
not released

Benchmarks

Each score carries the date it was published; we never infer or interpolate missing scores.

General reasoning

MMLU-Pro 85.3 as of 2026-05-21 source ↗
GPQA-Diamond 87.7 as of 2025-04-16 source ↗

Code

SWE-Bench Verified 71.7 as of 2025-04-16 source ↗
LiveCodeBench 80.8 as of 2026-05-21 source ↗

Math

MATH 99.2 as of 2026-05-21 source ↗
AIME 2024 90.3 as of 2026-05-21 source ↗
AIME 2025 88.3 as of 2026-05-21 source ↗

Available quantizations

None. The weights are not distributed, so there are no public quantizations.

Notable innovations

  • · Multimodal reasoning over text and images
  • · Step-change in SWE-bench Verified over o1

Sources