Kimi K2.6vsGPT-4
Kimi K2.6 | GPT-4 | |
|---|---|---|
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | 1T | — |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | 256k | 8k |
| 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. | $0.95 | $30.00 |
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. | $4.00 | $60.00 |
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. | $0.16 | — |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.5194Decart | $30.00Azure |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $2.45Decart | $60.00Azure |
| BenchmarksPublished by one model only | ||
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. | 65% | — |
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. | 80.2% | — |
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. | 62% | — |
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. | 89.6% | — |
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. | — | 67% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.2% | — |
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. | 34.7% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 90.5% | — |
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. | — | 86.4% |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | — | 92% |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 73.1% | — |
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Apr 21 2026 | Mar 14 2023 |
| Access | Open Weight | Proprietary |
Other comparisons
Frequently asked questions
Kimi K2.6 and GPT-4 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Kimi K2.6 is cheaper on both input and output: $0.95 vs $30.00 per million input tokens, and $4.00 vs $60.00 per million output tokens. GPT-4 shipped 1134 days before Kimi K2.6, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Kimi K2.6) vs 8k (GPT-4). Kimi K2.6 is open weight, while GPT-4 is proprietary.
Direct benchmark comparisons are unavailable — Kimi K2.6 and GPT-4 don't publish scores on any of the same benchmarks.
Kimi K2.6 was released by Moonshot AI on Apr 21 2026.
GPT-4 was released by OpenAI on Mar 14 2023.
Kimi K2.6 is cheaper on both input and output: $0.95 vs $30.00 per million input tokens, and $4.00 vs $60.00 per million output tokens. Rates are pay-as-you-go API prices verified on August 18, 2026.
Kimi K2.6 has a 256k context window; GPT-4 has 8k.
Kimi K2.6 is an open weight model released by Moonshot AI. GPT-4 is a proprietary model released by OpenAI.