Compare · ModelsLive · 2 picked · head to head
Gemini 1.5 Pro (May 2024) vs Llama 3.2 90B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 1.5 Pro (May 2024) wins on 4/5 benchmarks
Gemini 1.5 Pro (May 2024) wins 4 of 5 shared benchmarks. Leads in knowledge · math.
Category leads
knowledge·Gemini 1.5 Pro (May 2024)math·Gemini 1.5 Pro (May 2024)
Hype vs Reality
Attention vs performance
Gemini 1.5 Pro (May 2024)
#202 by perf·no signal
Llama 3.2 90B
#217 by perf·#18 by attention
Best value
Pricing unknown
Gemini 1.5 Pro (May 2024)
n/a
no price
Llama 3.2 90B
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 Pro (May 2024)Llama 3.2 90B
Balrog
Llama 3.2 90B leads by +6.3
Balrog · benchmarks AI agents on text-based adventure games, testing language understanding, strategic planning, and long-horizon reasoning.
Gemini 1.5 Pro (May 2024)
21.0
Llama 3.2 90B
27.3
GPQA diamond
Gemini 1.5 Pro (May 2024) leads by +6.4
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 Pro (May 2024)
27.8
Llama 3.2 90B
21.4
MATH level 5
Gemini 1.5 Pro (May 2024) leads by +1.3
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Gemini 1.5 Pro (May 2024)
40.8
Llama 3.2 90B
39.4
MMLU
Gemini 1.5 Pro (May 2024) leads by +7.5
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
Gemini 1.5 Pro (May 2024)
81.2
Llama 3.2 90B
73.7
OTIS Mock AIME 2024-2025
Gemini 1.5 Pro (May 2024) leads by +4.2
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 1.5 Pro (May 2024)
6.7
Llama 3.2 90B
2.5
Full benchmark table
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.2 90B |
|---|---|---|
Balrog Balrog · benchmarks AI agents on text-based adventure games, testing language understanding, strategic planning, and long-horizon reasoning. | 21.0 | 27.3 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 27.8 | 21.4 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 40.8 | 39.4 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 81.2 | 73.7 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 6.7 | 2.5 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| — | — | — | — | |
| — | — | — | — |