Compare · ModelsLive · 2 picked · head to head
GPT-3.5 Turbo (older v0613) vs Llama 3.1 405B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Llama 3.1 405B wins on 9/11 benchmarks
Llama 3.1 405B wins 9 of 11 shared benchmarks. Leads in knowledge · reasoning · general.
Category leads
knowledge·Llama 3.1 405Breasoning·Llama 3.1 405Bgeneral·Llama 3.1 405Bmath·Llama 3.1 405Bcoding·Llama 3.1 405B
Hype vs Reality
Attention vs performance
GPT-3.5 Turbo (older v0613)
#235 by perf·no signal
Llama 3.1 405B
#206 by perf·no signal
Best value
GPT-3.5 Turbo (older v0613)
GPT-3.5 Turbo (older v0613)
21.9 pts/$
$1.50/M
Llama 3.1 405B
n/a
no price
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Meta AI
$1.87T·Tier 1
Head to head
11 benchmarks · 2 models
GPT-3.5 Turbo (older v0613)Llama 3.1 405B
ARC AI2
Llama 3.1 405B leads by +10.5
AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval.
GPT-3.5 Turbo (older v0613)
83.2
Llama 3.1 405B
93.7
BBH
Llama 3.1 405B leads by +28.4
BIG-Bench Hard · a curated subset of 23 challenging tasks from BIG-Bench where language models previously failed to outperform average humans.
GPT-3.5 Turbo (older v0613)
48.8
Llama 3.1 405B
77.2
Dtbench
Llama 3.1 405B leads by +21.4
GPT-3.5 Turbo (older v0613)
14.2
Llama 3.1 405B
35.6
GPQA diamond
Llama 3.1 405B leads by +31.6
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-3.5 Turbo (older v0613)
2.9
Llama 3.1 405B
34.5
MATH level 5
Llama 3.1 405B leads by +38.1
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
GPT-3.5 Turbo (older v0613)
11.6
Llama 3.1 405B
49.8
MMLU
Llama 3.1 405B leads by +22.9
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
GPT-3.5 Turbo (older v0613)
56.4
Llama 3.1 405B
79.3
OpenBookQA
GPT-3.5 Turbo (older v0613) leads by +49.1
OpenBookQA · science questions that require combining a given core fact with broad common knowledge, mimicking an open-book exam setting.
GPT-3.5 Turbo (older v0613)
81.3
Llama 3.1 405B
32.3
OTIS Mock AIME 2024-2025
Llama 3.1 405B leads by +7.5
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-3.5 Turbo (older v0613)
2.1
Llama 3.1 405B
9.6
TriviaQA
GPT-3.5 Turbo (older v0613) leads by +3.1
TriviaQA · reading comprehension benchmark with trivia questions, requiring models to find and reason over evidence from provided documents.
GPT-3.5 Turbo (older v0613)
85.8
Llama 3.1 405B
82.7
WeirdML
Llama 3.1 405B leads by +17.9
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-3.5 Turbo (older v0613)
3.5
Llama 3.1 405B
21.4
Winogrande
Llama 3.1 405B leads by +15.2
WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs.
GPT-3.5 Turbo (older v0613)
63.2
Llama 3.1 405B
78.4
Full benchmark table
| Benchmark | GPT-3.5 Turbo (older v0613) | Llama 3.1 405B |
|---|---|---|
ARC AI2 AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval. | 83.2 | 93.7 |
BBH BIG-Bench Hard · a curated subset of 23 challenging tasks from BIG-Bench where language models previously failed to outperform average humans. | 48.8 | 77.2 |
Dtbench | 14.2 | 35.6 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 2.9 | 34.5 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 11.6 | 49.8 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 56.4 | 79.3 |
OpenBookQA OpenBookQA · science questions that require combining a given core fact with broad common knowledge, mimicking an open-book exam setting. | 81.3 | 32.3 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 2.1 | 9.6 |
TriviaQA TriviaQA · reading comprehension benchmark with trivia questions, requiring models to find and reason over evidence from provided documents. | 85.8 | 82.7 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 3.5 | 21.4 |
Winogrande WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs. | 63.2 | 78.4 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.00 | $2.00 | 4K tokens (~2 books) | $12.50 | |
| — | — | — | — |
People also compared