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. | 5.1B/8B/26B/31B | 130B |
| 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. | $0.04Darkbloom | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.10Modal | — |
| $15.50Darkbloom | — | |
| 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. | 25% | — |
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. | 80% | — |
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. | 19.5% | — |
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. | 26.5% | — |
AIME 2026Reasoning — single-answer accuracy on the 2026 invitational mathematics exam without tools | 89.2% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 84.3% | — |
MMMLUKnowledge — average accuracy on multilingual translations of MMLU | 88.4% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 85.2% | — |
Z-Bench (March 2023)Chinese-language evaluation — fully correct responses on ZhenFund’s 311-question evaluation of the March 2023 ChatGLM alpha | — | 40.2% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 76.9% | — |
MRCR v2 (8-needle) · 128k averageLong context — Tests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better. | 66.4% | — |
| Overview | ||
| Company | Z.ai | |
| Release date | Apr 2 2026 | Mar 14 2023 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Gemma 4vsClaude Fable 5.2ChatGLM-130BvsClaude Fable 5.2Gemma 4vsGPT-6.2 AstraChatGLM-130BvsGPT-6.2 AstraGemma 4vsMuse EmberChatGLM-130BvsMuse EmberGemma 4vsGrok 4.7ChatGLM-130BvsGrok 4.7Gemma 4vsDeepSeek-V4.1-Flash-1017ChatGLM-130BvsDeepSeek-V4.1-Flash-1017Gemma 4vsMistral Large 4ChatGLM-130BvsMistral Large 4Frequently asked questions
Gemma 4 and ChatGLM-130B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. ChatGLM-130B shipped 1115 days before Gemma 4, so benchmark comparisons should account for the intervening progress.
Gemma 4 has 5.1B/8B/26B/31B parameters, while ChatGLM-130B has 130B. Gemma 4 is open weight, while ChatGLM-130B is closed.
Direct benchmark comparisons are unavailable — Gemma 4 and ChatGLM-130B don't publish scores on any of the same benchmarks.