Models · Compare
Kimi K2.6 vs GPT-5.5
Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.
Specs
| Field | A: Kimi K2.6 | B: GPT-5.5 |
|---|---|---|
| Released | 2026-04-21 | 2026-04-23 |
| Developer | Moonshot AI | OpenAI |
| Openness | Open | Proprietary |
| License | Modified MIT | Proprietary |
| OSI-approved | no | no |
| Data released | no | no |
| Training code | no | no |
| Architecture | moe | unknown |
| Total params | 1T | — |
| Active params | 32B | — |
| Experts | 384 (8 active) | — |
| Context window | 262K | 1.0M |
| Attention | mla | unknown |
| Position enc. | rope | unknown |
| Pretraining tokens | — | — |
| Post-training | sft, rlhf | rlhf |
| Training hardware | — | — |
| $/M input | $0.95 | $5.00 |
| $/M output | $4.00 | $30.00 |
| Output tok/sec | 63.9 | 66.7 |
Benchmarks
Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.
General reasoning
| GPQA-Diamond | 90.5 2026-04-21 | 93.5 2026-05-21 |
Code
| SWE-Bench Verified | 80.2 2026-04-21 | — |
| LiveCodeBench | 89.6 2026-04-21 | — |
Context · A
April 21 2026 K2 refresh. Headline is Agent Swarm scaling to 300 sub-agents over 4000 coordinated steps, plus native video input and 262K context. Moonshot reports SWE-Bench Pro 58.6, narrowly ahead of GPT-5.4's 57.7 at release per the lab.
Context · B
Released April 23 2026, with GPT-5.5 and GPT-5.5 Pro hitting the API the next day. GPT-5.5 Instant replaced GPT-5.3 Instant as the ChatGPT default May 5 2026. Expanded context to 1M tokens; pricing above 272K input doubles input and 1.5x's output for the session.