Kimi K2 Thinking vs GPT-5.4 mini
Moonshot AI Kimi K2 Thinking | OpenAI GPT-5.4 mini | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Nov 6 2025 | Mar 17 2026 |
| Access | Open Weight | Proprietary |
| Specifications | ||
Parameters | 1T | — |
Context window | 256k | 400k |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given 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. | — | 32% |
Coding SWE-Bench VerifiedReal 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. | 71.3% | — |
| Timeline | ||
| Release gap | Kimi K2 Thinking shipped 131 days before GPT-5.4 mini | |
Which is better: Kimi K2 Thinking or GPT-5.4 mini?
Kimi K2 Thinking and GPT-5.4 mini don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Kimi K2 Thinking shipped 131 days before GPT-5.4 mini, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Kimi K2 Thinking) vs 400k (GPT-5.4 mini). Kimi K2 Thinking is open weight, while GPT-5.4 mini is proprietary.
Direct benchmark comparisons are unavailable — Kimi K2 Thinking and GPT-5.4 mini don't publish scores on any of the same benchmarks.
Frequently asked questions
Kimi K2 Thinking was released by Moonshot AI on Nov 6 2025.
GPT-5.4 mini was released by OpenAI on Mar 17 2026.
Kimi K2 Thinking has a 256k context window; GPT-5.4 mini has 400k.
Kimi K2 Thinking is an open weight model released by Moonshot AI. GPT-5.4 mini is a proprietary model released by OpenAI.