The Open-Source AI Stack
RSS
All models

Models · Compare

Gemini 3 Pro vs OLMo 3 32B Instruct

Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.

Specs

Field A: Gemini 3 Pro B: OLMo 3 32B Instruct
Released 2025-11-182025-11-20
Developer Google DeepMindAI2
Openness ProprietaryOpen
License ProprietaryApache-2.0
OSI-approved noyes
Data released noyes
Training code noyes
Architecture unknowndense
Total params 32B
Active params
Experts
Context window 1.0M66K
Attention unknowngqa
Position enc. unknownrope
Pretraining tokens 6.0T
Post-training rlhfsft, dpo, rlvr
Training hardware
$/M input $2.00
$/M output $12.00
Output tok/sec 132.9

Benchmarks

Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.

General reasoning

MMLU 85.4 2025-11-20
MMLU-Pro 89.8 2026-05-21
GPQA-Diamond 91.9 2025-11-18

Code

SWE-Bench Verified 76.2 2025-11-18
LiveCodeBench 91.7 2026-05-21

Math

MATH 96.1 2025-11-20
AIME 2024 76.8 2025-11-20
AIME 2025 95.7 2026-05-21

Held-out / arena

IFEval 89.0 2025-11-20

Context · A

DeepMind's flagship Gemini 3, announced by Sundar Pichai November 18 2025 with broader rollout on November 20. Shipped with a Deep Think mode and an agentic Gemini Agent surface, plus the new Antigravity platform for agent-first development.

Context · B

AI2's first 32B fully open frontier model, released November 20 2025 alongside a 7B and Base, Think, Instruct, and RL-Zero variants. Built on the Dolma 3 9.3T-token corpus (5.9T used for pretraining) and the Dolci post-training suite. All weights, data descriptions, intermediate checkpoints, and code released.

Gemini 3 Pro detail → · OLMo 3 32B Instruct detail →