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. | 109B | 6B |
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. | 10M | 8k |
| 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. | $0.08DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.24DeepInfra | — |
| $35.00DeepInfra · 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. | 20% | — |
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. | 32.8% | — |
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. | — | 35.9% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 57.2% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 74.3% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 90.6% | — |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 70.7% | — |
MMMU-Pro · standard and vision meanMultimodal reasoning — average across the standard and vision sets | 52.2% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 69.4% | — |
| Overview | ||
| Company | Meta | Z.ai |
| Release date | Apr 5 2025 | Jul 25 2023 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
LLaMA 4 ScoutvsClaude Fable 5.2CodeGeeX2-6BvsClaude Fable 5.2LLaMA 4 ScoutvsGPT-6.2 AstraCodeGeeX2-6BvsGPT-6.2 AstraLLaMA 4 ScoutvsGemini 4 HydrogenCodeGeeX2-6BvsGemini 4 HydrogenLLaMA 4 ScoutvsGrok 4.7CodeGeeX2-6BvsGrok 4.7LLaMA 4 ScoutvsDeepSeek-V4.1-Flash-1017CodeGeeX2-6BvsDeepSeek-V4.1-Flash-1017LLaMA 4 ScoutvsMistral Large 4CodeGeeX2-6BvsMistral Large 4Frequently asked questions
LLaMA 4 Scout and CodeGeeX2-6B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. CodeGeeX2-6B shipped 620 days before LLaMA 4 Scout, so benchmark comparisons should account for the intervening progress.
LLaMA 4 Scout has 109B parameters, while CodeGeeX2-6B has 6B. Context windows are 10M (LLaMA 4 Scout) vs 8k (CodeGeeX2-6B).
Direct benchmark comparisons are unavailable — LLaMA 4 Scout and CodeGeeX2-6B don't publish scores on any of the same benchmarks.