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. | — | 8B/70B/405B |
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. | 1M | 128k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $1.50 | — |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $7.50 | — |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.075 | — |
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. | — | $0.02DeepInfra |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.04DeepInfra |
| $675Google list price | $6.00DeepInfra · fp8 | |
| These models have no shared benchmark scores. | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 14% |
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. | — | 89% |
Terminal-Bench-Science 0.1Agentic scientific computing — The same command-line setup as Terminal-Bench, pointed at scientific work: the AI has to drive research tooling and computational workflows through to a result, rather than administer a machine. Version 0.1 is the first release of the task set, and scores run lower than on the general board. Higher is better. | 51.4% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 73.8% |
ARC-ChallengeReasoning — multiple-choice science questions from the AI2 Reasoning Challenge; unrelated to ARC-AGI | — | 96.9% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 49% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 73.3% |
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. | — | 87.3% |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | — | 91.6% |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | — | 96.8% |
OSWorld 2.1 · offlineAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.1, in its offline setting. Scores are not comparable with version 2.0. Higher is better. | 77.6% | — |
AutomationBench (Artificial Analysis)Business workflows — The same business-workflow test, run by Artificial Analysis rather than by the lab, and graded strict pass@1: a workflow counts only if the whole of it is right on the first attempt. Read it as a separate board from the lab-run AutomationBench scores. Higher is better. | 76.1% | — |
Vending-Bench 2 (USD)Business simulation — ending bank balance in US dollars in Andon Labs’ vending-business simulation; higher is better | 14549 | — |
Chartography · no toolsChart tasks — The same chart-centred test with no tools: the AI has to read each chart unaided. Scores run far lower than the with-tools version, so read the two as separate tests. Higher is better. | 66.6% | — |
| Overview | ||
| Company | Meta | |
| Release date | Nov 12 2026 | Jul 23 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 4 HydrogenvsClaude Fable 5.2LLaMA 3.1vsClaude Fable 5.2Gemini 4 HydrogenvsGPT-6.1 TerraLLaMA 3.1vsGPT-6.1 TerraGemini 4 HydrogenvsGrok 4.7LLaMA 3.1vsGrok 4.7Gemini 4 HydrogenvsDeepSeek-V4.1-Flash-1017LLaMA 3.1vsDeepSeek-V4.1-Flash-1017Gemini 4 HydrogenvsMistral Large 4LLaMA 3.1vsMistral Large 4Gemini 4 HydrogenvsKimi K3.1 ProLLaMA 3.1vsKimi K3.1 ProFrequently asked questions
Gemini 4 Hydrogen and LLaMA 3.1 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Gemini 4 Hydrogen has a verified first-party price for an available API: $1.50 per million input tokens and $7.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for LLaMA 3.1. LLaMA 3.1 shipped 842 days before Gemini 4 Hydrogen, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 4 Hydrogen) vs 128k (LLaMA 3.1). Gemini 4 Hydrogen is closed, while LLaMA 3.1 is open weight.
Direct benchmark comparisons are unavailable — Gemini 4 Hydrogen and LLaMA 3.1 don't publish scores on any of the same benchmarks.