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. | 117B | 30B |
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. | 128k | 200k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.00 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $0.00 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.00 |
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. | $0.03AkashML | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.15Near AI | — |
| $13.50Venice · int4 | $0.00Z.ai list price | |
| Benchmarks | ||
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. | 62.4% | 59.2% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 92.5% | 91.6% |
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. | 12% | — |
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. | — | 64% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 42.8% |
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. | 14.9% | — |
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. | 19% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 95.8% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 80.1% | — |
MMMLUKnowledge — average accuracy on multilingual translations of MMLU | 81.3% | — |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 90% | — |
HealthBench · full setHealthcare — physician rubric score on the full set of the original HealthBench evaluation | 57.6% | — |
HealthBench · hardHealthcare — physician rubric score on the hard subset of the original HealthBench evaluation | 30% | — |
HealthBench · consensusHealthcare — physician rubric score on the consensus subset of the original HealthBench evaluation | 89.9% | — |
| Overview | ||
| Company | OpenAI | Z.ai |
| Release date | Aug 5 2025 | Jan 19 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
gpt-oss-120bvsClaude Fable 5.2GLM-4.7-FlashvsClaude Fable 5.2gpt-oss-120bvsGemini 4 HydrogenGLM-4.7-FlashvsGemini 4 Hydrogengpt-oss-120bvsMuse EmberGLM-4.7-FlashvsMuse Embergpt-oss-120bvsGrok 4.7GLM-4.7-FlashvsGrok 4.7gpt-oss-120bvsDeepSeek-V4.1-Flash-1017GLM-4.7-FlashvsDeepSeek-V4.1-Flash-1017gpt-oss-120bvsMistral Large 4GLM-4.7-FlashvsMistral Large 4Frequently asked questions
gpt-oss-120b leads GLM-4.7-Flash on 2 of the 2 benchmarks they both report (SWE-Bench Verified, AIME 2025). Only GLM-4.7-Flash has a verified first-party price for an available API: $0.00 per million input tokens and $0.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for gpt-oss-120b. gpt-oss-120b shipped 167 days before GLM-4.7-Flash, so benchmark comparisons should account for the intervening progress.
gpt-oss-120b has 117B parameters, while GLM-4.7-Flash has 30B. Context windows are 128k (gpt-oss-120b) vs 200k (GLM-4.7-Flash).
On SWE-Bench Verified, gpt-oss-120b leads at 62.4% vs GLM-4.7-Flash at 59.2%. On AIME 2025, gpt-oss-120b leads at 92.5% vs GLM-4.7-Flash at 91.6%.