Compare · ModelsLive · 2 picked · head to head
Gemini 1.5 Flash (May 2024) vs Llama 3-70B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Llama 3-70B wins on 4/5 benchmarks
Llama 3-70B wins 4 of 5 shared benchmarks. Leads in general · knowledge.
Category leads
general·Llama 3-70Bknowledge·Llama 3-70Bmath·Gemini 1.5 Flash (May 2024)
Hype vs Reality
Attention vs performance
Gemini 1.5 Flash (May 2024)
#154 by perf·no signal
Llama 3-70B
#243 by perf·#18 by attention
Best value
Pricing unknown
Gemini 1.5 Flash (May 2024)
n/a
no price
Llama 3-70B
n/a
no price
Vendor risk
Who is behind the model
Google DeepMind
$4.20T·Tier 1
Meta AI
$1.87T·Tier 1
Head to head
5 benchmarks · 2 models
Gemini 1.5 Flash (May 2024)Llama 3-70B
Dtbench
Llama 3-70B leads by +4.6
Gemini 1.5 Flash (May 2024)
19.0
Llama 3-70B
23.6
GPQA diamond
Llama 3-70B leads by +0.3
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Gemini 1.5 Flash (May 2024)
20.5
Llama 3-70B
20.8
MATH level 5
Gemini 1.5 Flash (May 2024) leads by +2.6
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Gemini 1.5 Flash (May 2024)
25.1
Llama 3-70B
22.6
MMLU
Llama 3-70B leads by +1.9
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
Gemini 1.5 Flash (May 2024)
70.5
Llama 3-70B
72.4
OTIS Mock AIME 2024-2025
Llama 3-70B leads by +0.4
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 1.5 Flash (May 2024)
3.8
Llama 3-70B
4.2
Full benchmark table
| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3-70B |
|---|---|---|
Dtbench | 19.0 | 23.6 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 20.5 | 20.8 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 25.1 | 22.6 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 70.5 | 72.4 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 3.8 | 4.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| — | — | — | — | |
| — | — | — | — |