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. | 816B | 9B |
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 | ||
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. | $1.25BaseTen | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $4.25BaseTen | — |
| $463Modal | — | |
| These models have no shared benchmark scores. | ||
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | 60% | — |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 93% | — |
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. | — | 28.5% |
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. | — | 82.3% |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 76.4% | — |
MCP AtlasMulti-step tool use — Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | 89.2% | — |
JobBenchProfessional tool use — Tests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | 61.8% | — |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 1401 | — |
ZeroBench (tools, pass@5)Visual reasoning — percentage of 100 visual problems solved at least once in five attempts with tools | 50% | — |
SimpleVQA (with tools)Visual reasoning — accuracy on 2,024 English and Chinese visual questions with tools | 73.6% | — |
BabyVision (with tools)Visual reasoning — mean accuracy on 388 visual reasoning questions with tools | 80.2% | — |
HLE-Diamond (no tools)Reasoning — accuracy on the 1,000-question HLE-Diamond reasoning and knowledge subset without tools | 26.1% | — |
| Overview | ||
| Company | Meta | Z.ai |
| Release date | Oct 15 2026 | Jul 5 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Muse Spark OpenvsClaude Fable 5.2CodeGeeX4-ALL-9BvsClaude Fable 5.2Muse Spark OpenvsGPT-6.2 AstraCodeGeeX4-ALL-9BvsGPT-6.2 AstraMuse Spark OpenvsGemini 4 HydrogenCodeGeeX4-ALL-9BvsGemini 4 HydrogenMuse Spark OpenvsGrok 4.7CodeGeeX4-ALL-9BvsGrok 4.7Muse Spark OpenvsDeepSeek-V4.1-Flash-1017CodeGeeX4-ALL-9BvsDeepSeek-V4.1-Flash-1017Muse Spark OpenvsMistral Large 4CodeGeeX4-ALL-9BvsMistral Large 4Frequently asked questions
Muse Spark Open and CodeGeeX4-ALL-9B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. CodeGeeX4-ALL-9B shipped 832 days before Muse Spark Open, so benchmark comparisons should account for the intervening progress.
Muse Spark Open has 816B parameters, while CodeGeeX4-ALL-9B has 9B. Context windows are 1M (Muse Spark Open) vs 128k (CodeGeeX4-ALL-9B).
Direct benchmark comparisons are unavailable — Muse Spark Open and CodeGeeX4-ALL-9B don't publish scores on any of the same benchmarks.