Model

Gemini 1.0 Pro

CLOSED

Google · Gemini 1.0 family · released Dec 13, 2023

General-purpose 1.0 workhorse; powered Bard at launch; shut down on Gemini API (404s on gemini-1.0-pro).

ReasoningCodingVisionFunction callingTool useAgentic

620.1

Elo · rank #280

Parameters

Undisclosed

Active params

—

Context

32K tokens

Architecture

Dense Transformer decoder with multi-query attention

License

Proprietary (Google API/Vertex AI)

Languages

—

API price (in/out)

No hosted API

Modalities

text · vision · audio

Benchmark results

Bar shows position within the tracked field; marker = field best

AI2DVision73.9%#39

best: Molmo 72B · 96.3%

BIG-Bench HardReasoning75.0%#42

best: ERNIE 4.5 300B-A47B · 94.3%

ChartQAVision74.1%#37

best: MiniMax-VL-01 · 91.7%

DocVQAVision88.1%#38

best: Qwen2-VL-72B · 96.5%

DROPReasoning74.1#41

best: Hunyuan-T1 · 93.1

GSM8KMath86.5%#58

best: Llama 3.1 405B · 96.8%

HellaSwagReasoning84.7%#44

best: Claude 3 Opus · 95.4%

HumanEvalCoding67.7%#87

best: Claude Opus 4.5 · 99.4%

MATH-500Math32.6%#158

best: GPT-5 · 99.4%

MathVistaVision45.2%#57

best: Seed 2.1 Pro · 90.7%

MGSMMath63.5%#40

best: OpenAI o4-mini · 93.7%

MMLUKnowledge71.8%#137

best: OpenAI o3 · 92.9%

MMMUVision47.9%#99

best: Claude Fable 5 · 89.3%

TextVQAVision74.6%#19

best: Molmo 2 8B · 85.7%

VQAv2Vision71.2%#17

best: Reka Edge (2026) · 88.4%

Run it locally

Closed weights — available via API only. No local deployment.

Input / M tok

—

Output / M tok

—

Gemini 1.0 family

Elo progression across releases

Gemini 1.0 NanoDec 202391.9 Gemini 1.0 ProDec 2023620.1 Gemini 1.0 UltraFeb 2024992.0

Resources

DOCSai.google.dev/gemini-api/docs/deprecations

API price — · each benchmark row carries its own source badge (see methodology)