Model comparison
GPT-6 Luna vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.5 to 45.1 on the Noometry Index. GPT-6 Luna costs 8.6× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. GPT-6 Luna scores higher in 2 categories and Kimi K2.6 in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 56.8 to 35.6.
- The biggest single-benchmark swing is Furniture Assembly: 44.2% for GPT-6 Luna and 21.7% for Kimi K2.6.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- GPT-6 Luna accepts more context: 1.05M tokens versus 262K.
- Kimi K2.6 has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Luna | Kimi K2.6 | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 45.1 | 47.5 |
| Released | 2026-09-22 | 2026-04-20 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $0.10 | $0.95 |
| Output $ / M tokens | $0.50 | $4 |
| Results tracked | 18 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GPT-6 Luna: 54.7 (#24), Kimi K2.6: 50.5 (#41)
| Benchmark | GPT-6 Luna | Kimi K2.6 |
|---|---|---|
| LMArena WebDev | 1583 | 1509 |
| LMArena Coding | 1448 | 1488 |
| SWE-bench Verified | — | 76.7% |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| SciCode | — | 53.5% |
| WeirdML | — | 55.9% |
| ALE-Bench | — | 1,093 |
Agentic & Tool Use Not comparable
GPT-6 Luna: —, Kimi K2.6: 21.8 (#128)
| Benchmark | GPT-6 Luna | Kimi K2.6 |
|---|---|---|
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
GPT-6 Luna: 31.7 (#68), Kimi K2.6: 39.6 (#51)
| Benchmark | GPT-6 Luna | Kimi K2.6 |
|---|---|---|
| NYT Connections (extended) | 68.7% | 87.2% |
| LMArena Hard Prompts | 1415 | 1470 |
| CritPt | — | 8% |
| Chess Puzzles | — | 26% |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LMCA | — | 37.3% |
| Epoch Capabilities Index | — | 151.03 |
Math Kimi K2.6 leads
GPT-6 Luna: 35.6 (#140), Kimi K2.6: 56.8 (#34)
| Benchmark | GPT-6 Luna | Kimi K2.6 |
|---|---|---|
| LMArena Math | 1396 | 1475 |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| ProofBench | — | 16% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Kimi K2.6 leads
GPT-6 Luna: 40.1 (#110), Kimi K2.6: 53.9 (#48)
| Benchmark | GPT-6 Luna | Kimi K2.6 |
|---|---|---|
| LMArena Expert | 1458 | 1491 |
| GPQA Diamond | — | 90.8% |
| SimpleQA Verified | — | 34.9% |
| Vectara Hallucination Rate | — | 10.8% |
Multimodal GPT-6 Luna leads
GPT-6 Luna: 42.0 (#27), Kimi K2.6: 31.8 (#95)
| Benchmark | GPT-6 Luna | Kimi K2.6 |
|---|---|---|
| Furniture Assembly | 44.2% | 21.7% |
| LMArena Vision | — | 1282 |
| Blueprint-Bench 2 | — | 3.9% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
GPT-6 Luna: 51.0 (#111), Kimi K2.6: 55.1 (#35)
| Benchmark | GPT-6 Luna | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1390 | 1446 |
| LMArena Chinese | 1425 | 1521 |
| LMArena Russian | 1392 | 1446 |
| LMArena Spanish | 1416 | 1463 |
| LMArena French | — | 1471 |
| LMArena German | — | 1449 |
| LMArena Japanese | — | 1442 |
| LMArena Korean | — | 1428 |
Instruction Following Kimi K2.6 leads
GPT-6 Luna: 74.7 (#85), Kimi K2.6: 76.5 (#40)
| Benchmark | GPT-6 Luna | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1414 | 1451 |
Long Context Kimi K2.6 leads
GPT-6 Luna: 43.3 (#95), Kimi K2.6: 44.9 (#50)
| Benchmark | GPT-6 Luna | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1417 | 1468 |
Writing & Preference Kimi K2.6 leads
GPT-6 Luna: 58.4 (#115), Kimi K2.6: 68.7 (#25)
| Benchmark | GPT-6 Luna | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1392 | 1455 |
| LMArena Creative Writing | 1357 | 1434 |
| LMArena Multi-Turn | 1400 | 1453 |
| EQ-Bench Creative Writing | — | 1725 |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is GPT-6 Luna better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.5 to 45.1 on the Noometry Index. GPT-6 Luna costs 8.6× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Which is cheaper, GPT-6 Luna or Kimi K2.6?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is GPT-6 Luna or Kimi K2.6 better for coding?
GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 50.5 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 262K.
How many benchmarks do GPT-6 Luna and Kimi K2.6 share?
16 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and Kimi K2.6 has 51.