Compare · ModelsLive · 2 picked · head to head

GPT-4 (older v0314) vs Llama 3.3 70B Instruct

Side by side · benchmarks, pricing, and signals you can act on.

Winner summary

Llama 3.3 70B Instruct wins 3 of 5 shared benchmarks. Leads in arena · knowledge · math.

Category leads
coding·GPT-4 (older v0314)arena·Llama 3.3 70B Instructknowledge·Llama 3.3 70B Instructmath·Llama 3.3 70B Instruct

Head to head · from the data · data as of 2026-11-21

  • Benchmarks · GPT-4 (older v0314) leads on 2 of 5 shared benchmarks (Aider · Code Editing, MMLU), Llama 3.3 70B Instruct on 3 (Chatbot Arena Elo · Overall, GPQA diamond, OTIS Mock AIME 2024-2025)
  • Price · GPT-4 (older v0314) input $30.00/M vs Llama 3.3 70B Instruct $0.71/M, Llama 3.3 70B Instruct is 98% cheaper (OpenRouter list price, as of 2026-11-21)
  • Cheapest provider · Llama 3.3 70B Instruct at DeepInfra $0.10/M input (of 7 offers) as of 2026-11-21
  • Context · GPT-4 (older v0314) 8K tokens vs Llama 3.3 70B Instruct 131K tokens
  • Released · GPT-4 (older v0314) May 28, 2023 vs Llama 3.3 70B Instruct Dec 6, 2024 · 19 months apart
  • Open weights · Llama 3.3 70B Instruct has open weights (on Hugging Face as meta-llama/Llama-3.3-70B-Instruct)
  • Price history · GPT-4 (older v0314) OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-21

Sources · scores from public leaderboards, list prices and provider offers from OpenRouter, price moves from the BenchGecko changelog (5% or more, held in the next daily check), Gecko tests run by BenchGecko.

Hype vs Reality
GPT-4 (older v0314)
#92 by perf·no signal
QUIET
Llama 3.3 70B Instruct
#232 by perf·#19 by attention
QUIET
Best value
41.7x better value than GPT-4 (older v0314)
GPT-4 (older v0314)
1.2 pts/$
$45.00/M
Llama 3.3 70B Instruct
51.0 pts/$
$0.71/M
Vendor risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Meta logo
Meta AI
$1.44T·Tier 1
Low risk
Head to head
GPT-4 (older v0314)Llama 3.3 70B Instruct
Aider · Code Editing
GPT-4 (older v0314) leads by +6.8
GPT-4 (older v0314)
66.2
Llama 3.3 70B Instruct
59.4
Chatbot Arena Elo · Overall
Llama 3.3 70B Instruct leads by +32.0
GPT-4 (older v0314)
1285.8
Llama 3.3 70B Instruct
1317.8
GPQA diamond
Llama 3.3 70B Instruct leads by +16.9
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-4 (older v0314)
14.3
Llama 3.3 70B Instruct
31.2
MMLU
GPT-4 (older v0314) leads by +0.1
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
GPT-4 (older v0314)
81.9
Llama 3.3 70B Instruct
81.7
OTIS Mock AIME 2024-2025
Llama 3.3 70B Instruct leads by +4.6
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-4 (older v0314)
0.5
Llama 3.3 70B Instruct
5.0
Full benchmark table
BenchmarkGPT-4 (older v0314)Llama 3.3 70B Instruct
Aider · Code Editing
66.259.4
Chatbot Arena Elo · Overall
1285.81317.8
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
14.331.2
MMLU
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
81.981.7
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
0.55.0
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
OpenAI logoGPT-4 (older v0314)$30.00$60.008K tokens (~4 books)$375.00
Meta logoLlama 3.3 70B Instruct$0.71$0.71131K tokens (~66 books)$7.10
GPT-4 (older v0314) leads on 2 of 5 shared benchmarks (Aider · Code Editing, MMLU), Llama 3.3 70B Instruct on 3 (Chatbot Arena Elo · Overall, GPQA diamond, OTIS Mock AIME 2024-2025)