ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GPT-5.6 LunavsKimi K3

GPT-5.6 Luna and Kimi K3 split their 6 shared benchmarks evenly. GPT-5.6 Luna is 12.9x cheaper per token. GPT-5.6 Luna has the larger context window (1.1M tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
3 – 3
even split
Cheaper per token
GPT-5.6 Luna
12.9x cheaper, input + output
Larger context
GPT-5.6 Luna
1.1M tokens
Provider uptime (30d)
95.3757% · 100%
OpenAI · Moonshot AI
GPT-5.6 Luna
OpenAI · released 2026-07-09
textvision
Context
1.1M
Max out
128K
Input /1M
$0.2
Output /1M
$1.2
Cached /1M
$0.02
Scores
8 · 6 core
Kimi K3
Moonshot AI · released 2026-07-16
textvision
Context
1M
Max out
1.0M
Input /1M
$3
Output /1M
$15
Cached /1M
$0.3
Scores
59 · 8 core
Quality

Benchmark matrix

BenchmarkGPT-5.6 LunaKimi K3ΔEdge
Reported by both · 6
GPQA Diamond92.3% 93.5% -1.2 ptKimi K3
DeepSWE v1.167.2% 67.3% -0.1 ptKimi K3
FrontierMath Tier 4 v2 (Epoch AI run)61% epoch39% epoch+22 ptGPT-5.6 Luna
FrontierMath Tiers 1-3 v2 (Epoch AI run)82.1% epoch72.2% epoch+9.9 ptGPT-5.6 Luna
OTIS Mock AIME 2024-2025 (Epoch AI run)98.3% epoch97.2% epoch+1.1 ptGPT-5.6 Luna
SimpleQA Verified41% epoch50.6% epoch-9.6 ptKimi K3
Only GPT-5.6 Luna reports · 1
SWE-Bench Pro62.7% not reported
Only Kimi K3 reports · 51
AIME 2026not reported96.7% matharena
Humanity's Last Exam (no tools)not reported43.5%
AA-Briefcasenot reported1548
AA-LCRnot reported74.7%
Agents' Last Examnot reported28.3%
APEX-Agentsnot reported41%
AutomationBenchnot reported30.8%
BabyVision (with Python)not reported85.7%
BrowseComp (1M context, no compaction)not reported90.4%
BrowseComp (context compaction)not reported91.2%
CharXiv Reasoning (no tools)not reported84.8%
CharXiv Reasoning (with Python)not reported91.3%
CorpFin v2not reported71.6%
CritPtnot reported23.4%
DeepSearchQA (F1)not reported95%
DeepSWE v1.1 (Kimi Code)not reported67.5%
Finance Agent v2not reported54.4%
FrontierSWEnot reported81.2%
GDPval-AA v2not reported1686
Harvey Lab-AAnot reported94.6%
Humanity's Last Exam (with tools)not reported56%
JobBenchnot reported54.3%
Kimi Code Bench 2.0not reported72.9%
Legal Research Benchnot reported44.2%
MathVision (no tools)not reported94.3%
MathVision (with Python)not reported97.8%
MCP-Atlasnot reported84.2%
MCPMark-Verifiednot reported94.5%
MLS-Bench-Litenot reported48.3%
MMMU-Pro (no tools)not reported81.6%
MMMU-Pro (with Python)not reported83.4%
MMVUnot reported82.1%
OfficeQA Pronot reported63.3%
OmniDocBenchnot reported91.1%
OSWorld 2.0not reported58.3%
OSWorld-Verifiednot reported84.8%
PerceptionBenchnot reported58.5%
PostTrainBenchnot reported36.6%
ProgramBenchnot reported77.8%
ResearchRubricsnot reported76.2%
SaaS-Benchnot reported60.1%
SciCodenot reported58.7%
SpreadsheetBench 2not reported34.8%
SWE-Marathonnot reported42%
tau3-Bankingnot reported33.4%
Terminal-Bench 2.1not reported88.3%
Toolathlon-Verifiednot reported76.5%
Video-MME (with subtitles)not reported90%
WorldVQA ForceAnswernot reported51%
ZeroBench pass@5 (no tools)not reported23%
ZeroBench pass@5 (with Python)not reported41%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is GPT-5.6 Luna minus Kimi K3 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecGPT-5.6 LunaKimi K3Edge
Context window1.1M tokens1M tokensGPT-5.6 Luna
Max output128K tokens1.0M tokensKimi K3
Input price / 1M$0.2 $3 GPT-5.6 Luna
Output price / 1M$1.2 $15 GPT-5.6 Luna
Cached input / 1M$0.02 $0.3 GPT-5.6 Luna
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$1.4$18GPT-5.6 Luna
Modalitiestext · visiontext · visionTie
Released2026-07-092026-07-16
Cited benchmark scores859
Reliability

Provider status

All providers
More matchups

GPT-5.6 Luna vs …

More matchups

Kimi K3 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GPT-5.6 Luna and Kimi K3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.