Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 70B | — |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 128k | 200k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.10DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.32DeepInfra | — |
| $36.00DeepInfra · turbo · fp8 | — | |
| These models have no shared benchmark scores. | ||
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 88.4% | — |
MATHReasoning — accuracy on the original competition mathematics test set | 77% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 50.5% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 68.9% | — |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 86% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 91.1% | — |
| Overview | ||
| Company | Meta | OpenAI |
| Release date | Dec 6 2024 | May 16 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
LLaMA 3.3vsClaude Fable 5.2codex-mini-latestvsClaude Fable 5.2LLaMA 3.3vsGemini 4 Carboncodex-mini-latestvsGemini 4 CarbonLLaMA 3.3vsGrok 4.7codex-mini-latestvsGrok 4.7LLaMA 3.3vsDeepSeek-V4.1-Flash-1017codex-mini-latestvsDeepSeek-V4.1-Flash-1017LLaMA 3.3vsMistral Large 4codex-mini-latestvsMistral Large 4LLaMA 3.3vsKimi K3.1 Procodex-mini-latestvsKimi K3.1 ProFrequently asked questions
LLaMA 3.3 and codex-mini-latest don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. LLaMA 3.3 shipped 161 days before codex-mini-latest, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (LLaMA 3.3) vs 200k (codex-mini-latest). LLaMA 3.3 is open weight, while codex-mini-latest is closed.
Direct benchmark comparisons are unavailable — LLaMA 3.3 and codex-mini-latest don't publish scores on any of the same benchmarks.