GPT-5.6 Luna vs Kimi K2.6.
Verdict by category, tale of the tape, shared benchmarks only, and cost at three workloads — all from the tracked data.
Verdict by category
| Category | GPT-5.6 Luna | Kimi K2.6 | Winner |
|---|---|---|---|
| League Score | 70.4 | 69.7 | GPT-5.6 Luna |
| Coding (SWE-bench %) | — | 80.2 | — |
| Reasoning (GPQA %) | 92.3 | 90.5 | GPT-5.6 Luna |
| Context (tokens) | 1050000 | 262144 | GPT-5.6 Luna |
| Speed (tok/s) | — | — | — |
| Price (blended $/1M) | $0.45 | $1.71 | GPT-5.6 Luna (cheaper) |
Tale of the tape
| Spec | GPT-5.6 Luna | Kimi K2.6 |
|---|---|---|
| Maker | OpenAI | Moonshot AI |
| Released | Jul 9, 2026 | Apr 20, 2026 |
| League Score | 70 | 70 |
| Context | 1,050,000 tokens | 262,144 tokens |
| Max output | 128,000 | — |
| $/1M input | $0.20 | $0.95 |
| $/1M output | $1.20 | $4.00 |
| Weights | Closed | Open |
| Speed | — | — |
Head-to-head benchmarks (shared only)
| Benchmark | GPT-5.6 Luna | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 92.3 | 90.5 |
Cost at three workloads
| Workload | GPT-5.6 Luna | Kimi K2.6 |
|---|---|---|
| Light — 1M in / 250K out | $0.50 | $1.95 |
| Standard — 10M in / 2.5M out | $5.00 | $19.50 |
| Long-context — 50M in / 5M out | $16.00 | $67.50 |
The pick
Pick GPT-5.6 Luna if you want the higher overall League Score; you need the bigger context window; you want the lower running cost.
Pick Kimi K2.6 if you want downloadable weights / self-hosting; coding is the priority.
All figures from the model database — sources and dates on each model page. Cost your own workload or compare a different pair.
Frequently asked questions
Which is better overall, GPT-5.6 Luna or Kimi K2.6?
On overall League Score they are effectively tied — GPT-5.6 Luna scores 70 and Kimi K2.6 scores 70. The category verdicts on this page are where the real differences live.
Which is cheaper, GPT-5.6 Luna or Kimi K2.6?
GPT-5.6 Luna is cheaper: $0.45 vs $1.71 blended per 1M tokens (3:1 input/output mix) — about 3.8x less per token.
Which has the bigger context window, GPT-5.6 Luna or Kimi K2.6?
GPT-5.6 Luna, with 1.1M of context against 262.1K for Kimi K2.6.
Which is better at reasoning, GPT-5.6 Luna or Kimi K2.6?
GPT-5.6 Luna leads on GPQA Diamond, 92.3% vs 90.5% on graduate-level science questions.
Are GPT-5.6 Luna and Kimi K2.6 open source?
GPT-5.6 Luna is closed weights — API access only; Kimi K2.6 is open weights — it can be downloaded and self-hosted.