Benchmark scores
Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.
LLM Comparison
Kimi K3 vs GPT-5.6 Luna: benchmark scores, pricing & comparison.
Side-by-side Kimi K3 vs GPT-5.6 Luna comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.
Verdict: Kimi K3 ranks higher (#28 vs #37) and wins 8 of 12 shared benchmarks; GPT-5.6 Luna costs less ($1.00/$6.00 vs $3.00/$15.0 per 1M tokens).
Rank #28 vs #37AskClash overall scores 55.7 vs 51.7.
Pricing $3.00/$15.0 vs $1.00/$6.00Input and output token prices per 1M tokens when published.
Open Weight vs ProprietaryMoonshot AI vs OpenAI.
Kimi K3 vs GPT-5.6 Luna benchmark comparison
Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.
| Metric | Kimi K3 | GPT-5.6 Luna |
|---|---|---|
| Overall Score | 55.7 | 51.7 |
| Leaderboard Rank | #28 | #37 |
| ACB | 57.7 | 56.1 |
| RWT | 8.0 | 9.5 |
| Coding Agent Index | 51.9 | 75.0 |
| HLE | 43.5 | 39.5 |
| GPQA | 93.5 | 92.3 |
| SWE-Pro | — | 62.7 |
| SWE-Atlas | 66.1 | 81.0 |
| Terminal-Bench | 12.6 | 11.6 |
| DeepSWE | 68.5 | 67.2 |
| GDPval-AA | 1668.0 | 1592.0 |
| MCP Atlas | 84.2 | — |
| Finance Agent | 53.1 | 55.0 |
| CharXiv | 84.8 | — |
| MMMU-Pro | 81.6 | 78.4 |
| ARC-AGI 2 | 60.4 | 59.5 |
| MRCR | — | 41.3 |
| Input Price (per 1M tokens) | $3.00 | $1.00 |
| Output Price (per 1M tokens) | $15.0 | $6.00 |
| Context Window | 1M | 1M |
| Benchmarks Published | 16 | 15 |
Kimi K3 vs GPT-5.6 Luna head-to-head charts
Kimi K3 leads 9 and GPT-5.6 Luna leads 4 of 13 shared benchmarks. GPT-5.6 Luna is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.
Kimi K3GPT-5.6 Luna
Overall
ACB
RWT
Coding Agent Index
HLE
GPQA
SWE-Atlas
Terminal-Bench
DeepSWE
GDPval-AA
Finance Agent
MMMU-Pro
Kimi K3
Input$3.00
Output$15.0
Workload$6.00
Context1M
GPT-5.6 Luna
Input$1.00
Output$6.00
Workload$2.20
Context1M
Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.
More Kimi K3 and GPT-5.6 Luna comparisons
Explore how Kimi K3 and GPT-5.6 Luna stack up against other top-ranked LLMs.
How to read this comparison
Token pricing
Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.
Coverage matters
Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.
This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.