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 | 27B/35B/122B |
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 | — | |
| Benchmarks | ||
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% | 78.9% |
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% | 86.6% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 80.5% | 86.7% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 73.4% | 83.9% |
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% | — |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 72% |
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. | — | 49.4% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 93.4% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 63.8% |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 25.3% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 47.5% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 76.1% |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 92.3% | — |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | — | 58% |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 77.2% |
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% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 76.9% |
| Overview | ||
| Company | Meta | Qwen |
| Release date | Apr 5 2025 | Feb 24 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
LLaMA 4 MaverickvsClaude Fable 5.2Qwen3.5 MediumvsClaude Fable 5.2LLaMA 4 MaverickvsGPT-6.2 AstraQwen3.5 MediumvsGPT-6.2 AstraLLaMA 4 MaverickvsGemini 4 NeonQwen3.5 MediumvsGemini 4 NeonLLaMA 4 MaverickvsGrok 4.7Qwen3.5 MediumvsGrok 4.7LLaMA 4 MaverickvsDeepSeek-V4.1-Flash-1017Qwen3.5 MediumvsDeepSeek-V4.1-Flash-1017LLaMA 4 MaverickvsMistral Large 4Qwen3.5 MediumvsMistral Large 4Frequently asked questions
Qwen3.5 Medium leads LLaMA 4 Maverick on 4 of the 4 benchmarks they both report (LiveCodeBench, GPQA Diamond, MMLU-Pro, MMMU). LLaMA 4 Maverick shipped 325 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.
LLaMA 4 Maverick has 400B parameters, while Qwen3.5 Medium has 27B/35B/122B. Context windows are 1M (LLaMA 4 Maverick) vs 256k (Qwen3.5 Medium).
On LiveCodeBench, Qwen3.5 Medium leads at 78.9% vs LLaMA 4 Maverick at 43.4%. On GPQA Diamond, Qwen3.5 Medium leads at 86.6% vs LLaMA 4 Maverick at 69.8%. On MMLU-Pro, Qwen3.5 Medium leads at 86.7% vs LLaMA 4 Maverick at 80.5%. On MMMU, Qwen3.5 Medium leads at 83.9% vs LLaMA 4 Maverick at 73.4%.