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. | 2.8T | 21B |
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. | — | $0.018Darkbloom |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.09Darkbloom |
| — | $8.10Darkbloom · fp8 | |
| Benchmarks | ||
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. | 70% | 17.3% |
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. | — | 60.7% |
BenchCADCAD programming — Can the AI do mechanical design as code? Given a drawing or a description of an industrial part — a gear, a spring, a drill bit — it has to write or edit the parametric CAD program that builds it, and the program is run to check the shape really comes out right. Higher is better. | 92.7% | — |
Terminal-Bench 4.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better. | 65.7% | — |
Terminal-Bench-Science 0.1Agentic scientific computing — The same command-line setup as Terminal-Bench, pointed at scientific work: the AI has to drive research tooling and computational workflows through to a result, rather than administer a machine. Version 0.1 is the first release of the task set, and scores run lower than on the general board. Higher is better. | 38.1% | — |
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. | — | 10.9% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 71.5% |
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. | — | 85.3% |
Chartography · with toolsChart tasks — A chart-centred test run with tools available to the AI, reported separately from the chart-reading benchmarks above it. Higher is better. | 90.2% | — |
GDP.PDFDocument comprehension — Real professional PDFs — filings, reports, technical documents — with questions an expert in that field would ask. Tests whether the AI reads the page as a document, layout and figures included, rather than as loose text. Higher is better. | 34.6% | — |
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Oct 23 2026 | Aug 5 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Kimi K3.1 ProvsClaude Haiku 5.5gpt-oss-20bvsClaude Haiku 5.5Kimi K3.1 ProvsGemini 4 Argongpt-oss-20bvsGemini 4 ArgonKimi K3.1 ProvsMuse Spark Opengpt-oss-20bvsMuse Spark OpenKimi K3.1 ProvsGrok 4.7gpt-oss-20bvsGrok 4.7Kimi K3.1 ProvsDeepSeek-V4.1-Flash-1017gpt-oss-20bvsDeepSeek-V4.1-Flash-1017Kimi K3.1 ProvsMistral Large 4gpt-oss-20bvsMistral Large 4Frequently asked questions
Kimi K3.1 Pro leads gpt-oss-20b on 1 of the 1 benchmark they both report (Humanity's Last Exam). gpt-oss-20b shipped 444 days before Kimi K3.1 Pro, so benchmark comparisons should account for the intervening progress.
Kimi K3.1 Pro has 2.8T parameters, while gpt-oss-20b has 21B. Context windows are 1M (Kimi K3.1 Pro) vs 128k (gpt-oss-20b).
On Humanity's Last Exam · with tools, Kimi K3.1 Pro leads at 70% vs gpt-oss-20b at 17.3%.