Nemotron 3 SupervsGPT-4 Turbo

Nemotron 3 Super
GPT-4 Turbo
Specifications
Parameters
120B
Context window
1M128k
API pricing
Input price
$10.00
Output price
$30.00
Benchmarks
GPQA Diamond
79.2%42.5%
Benchmarks
SWE-Bench Verified
60.5%
AA Intelligence Index
36
Overview
CompanyNVIDIAOpenAI
Release dateMar 11 2026Nov 6 2023
AccessOpen SourceProprietary

Other comparisons

Nemotron 3 SupervsClaude Opus 5GPT-4 TurbovsClaude Opus 5Nemotron 3 SupervsGemini 3.7 FlashGPT-4 TurbovsGemini 3.7 FlashNemotron 3 SupervsMuse GlimmerGPT-4 TurbovsMuse GlimmerNemotron 3 SupervsGrok 4.6GPT-4 TurbovsGrok 4.6Nemotron 3 SupervsDeepSeek-V4-Pro-0813GPT-4 TurbovsDeepSeek-V4-Pro-0813Nemotron 3 SupervsMistral Medium 3.5GPT-4 TurbovsMistral Medium 3.5

Frequently asked questions

Nemotron 3 Super leads GPT-4 Turbo on 1 of the 1 benchmark they both report (GPQA Diamond). Only GPT-4 Turbo has a verified first-party API price: $10.00 per million input tokens and $30.00 per million output tokens. No pay-as-you-go API rate is tracked for Nemotron 3 Super. GPT-4 Turbo shipped 856 days before Nemotron 3 Super, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Nemotron 3 Super) vs 128k (GPT-4 Turbo). Nemotron 3 Super is open source, while GPT-4 Turbo is proprietary.

On GPQA Diamond, Nemotron 3 Super leads at 79.2% vs GPT-4 Turbo at 42.5%.

Nemotron 3 Super was released by NVIDIA on Mar 11 2026.

GPT-4 Turbo was released by OpenAI on Nov 6 2023.

Nemotron 3 Super leads on GPQA Diamond — Nemotron 3 Super 79.2% vs GPT-4 Turbo 42.5%.

Only GPT-4 Turbo has a verified first-party API price: $10.00 per million input tokens and $30.00 per million output tokens. No pay-as-you-go API rate is tracked for Nemotron 3 Super. Rates are pay-as-you-go API prices verified on August 18, 2026.

Nemotron 3 Super has a 1M context window; GPT-4 Turbo has 128k.

Nemotron 3 Super is an open source model released by NVIDIA. GPT-4 Turbo is a proprietary model released by OpenAI.