Compare · ModelsLive · 2 picked · head to head

gpt-oss-120b vs Llama 3.1 405B

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

Winner summary

gpt-oss-120b wins 3 of 4 shared benchmarks. Leads in knowledge · math · coding.

Category leads
knowledge·gpt-oss-120bmath·gpt-oss-120breasoning·Llama 3.1 405Bcoding·gpt-oss-120b
Hype vs Reality
gpt-oss-120b
#108 by perf·no signal
QUIET
Llama 3.1 405B
#153 by perf·no signal
QUIET
Best value
gpt-oss-120b
428.3 pts/$
$0.11/M
Llama 3.1 405B
no price
Vendor risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Meta logo
Meta AI
$1.50T·Tier 1
Low risk
Head to head
gpt-oss-120bLlama 3.1 405B
GPQA diamond
gpt-oss-120b leads by +33.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
gpt-oss-120b
67.7
Llama 3.1 405B
34.5
OTIS Mock AIME 2024-2025
gpt-oss-120b leads by +79.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
gpt-oss-120b
88.9
Llama 3.1 405B
9.6
SimpleBench
Llama 3.1 405B leads by +1.1
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
gpt-oss-120b
6.5
Llama 3.1 405B
7.6
WeirdML
gpt-oss-120b leads by +26.8
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
gpt-oss-120b
48.2
Llama 3.1 405B
21.4
Full benchmark table
Benchmarkgpt-oss-120bLlama 3.1 405B
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
67.734.5
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
88.99.6
SimpleBench
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
6.57.6
WeirdML
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
48.221.4
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
OpenAI logogpt-oss-120b$0.04$0.18131K tokens (~66 books)$0.74
Meta logoLlama 3.1 405B
People also compared