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. | 400B | — |
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 | 256k |
| 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. | $0.35Parasail | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.00Parasail | — |
| $120Parasail · 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. | 29% | — |
NL2Repo-BenchRepo-level code generation — Tests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. | — | 42.9% |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 43.4% | — |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 65.4% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 69.8% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 80.5% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 92.3% | — |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 73.7% | — |
MMMU-Pro · standard and vision meanMultimodal reasoning — average across the standard and vision sets | 59.6% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 73.4% | — |
| Overview | ||
| Company | Meta | Qwen |
| Release date | Apr 5 2025 | Apr 14 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
LLaMA 4 MaverickvsClaude Fable 5.2Qwen3.6-Max-PreviewvsClaude Fable 5.2LLaMA 4 MaverickvsGPT-6.2 AstraQwen3.6-Max-PreviewvsGPT-6.2 AstraLLaMA 4 MaverickvsGemini 4 NeonQwen3.6-Max-PreviewvsGemini 4 NeonLLaMA 4 MaverickvsGrok 4.7Qwen3.6-Max-PreviewvsGrok 4.7LLaMA 4 MaverickvsDeepSeek-V4.1-Flash-1017Qwen3.6-Max-PreviewvsDeepSeek-V4.1-Flash-1017LLaMA 4 MaverickvsMistral Large 4Qwen3.6-Max-PreviewvsMistral Large 4Frequently asked questions
LLaMA 4 Maverick and Qwen3.6-Max-Preview don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. LLaMA 4 Maverick shipped 374 days before Qwen3.6-Max-Preview, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (LLaMA 4 Maverick) vs 256k (Qwen3.6-Max-Preview). LLaMA 4 Maverick is open weight, while Qwen3.6-Max-Preview is closed.
Direct benchmark comparisons are unavailable — LLaMA 4 Maverick and Qwen3.6-Max-Preview don't publish scores on any of the same benchmarks.