Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview
Kimi K2.6
Kimi K2.6 is an open-weight model from Moonshot AI, released Apr 20, 2026. It ranks #44 of 351 on the LMArena text leaderboard with a rating of 1455. It costs $0.65 per million input tokens and $3.41 per million output tokens, with a 256K-token context window.
- Developer
- Moonshot AI
- Released
- Apr 20, 2026
- Context window
- 256K
- Price in / out, per 1M tokens
- $0.65 / $3.41
- Weights
- Open · Modified MIT
- Inputs
- Text, Images
- Reasoning
- Yes
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 348.2K
- Hugging Face likes
- 1.6K
The rating LMArena published at each update since Apr 22, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 76.20% | 39 / 85 | $0.27 | |
| Vibe Code BenchCoding | 37.89% | 69 / 115 | $1.93 | |
| LiveCodeBenchCoding | 86.77% | 20 / 143 | $0.95 / $4 | |
| Tax Agent BenchFinance | 12.40% | 58 / 76 | $0.57 | |
| Legal Research BenchLaw | 15.87% | 67 / 85 | $1.52 | |
| MedCodeMedicine | 40.14% | 68 / 107 | $0.95 / $4 | |
| GPQA DiamondReasoning | 89.14% | 31 / 138 | $0.95 / $4 | |
| MMLU-ProReasoning | 87.57% | 25 / 138 | $0.95 / $4 | |
| MMMUReasoning | 86.30% | 21 / 93 | $0.95 / $4 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1455 | 44 / 351 | 40K |
| CodingLMArena | 1488 | 37 / 346 | 11.1K |
| MathLMArena | 1474 | 40 / 339 | 2.1K |
| Creative writingLMArena | 1434 | 58 / 349 | 6.3K |
| Instruction followingLMArena | 1451 | 51 / 351 | 13.2K |
| Hard promptsLMArena | 1470 | 46 / 351 | 26.1K |
| Multi-turnLMArena | 1453 | 61 / 349 | 6.9K |
| Long queriesLMArena | 1468 | 43 / 330 | 17K |
| ExpertLMArena | 1490 | 37 / 305 | 3.9K |
| Legal and governmentIndustries | 1461 | 50 / 325 | 3K |
| Medicine and healthcareIndustries | 1457 | 57 / 325 | 2.9K |
| Business and financeIndustries | 1445 | 50 / 344 | 7.9K |
| ChineseLanguages | 1520 | 32 / 328 | 2.3K |
| SpanishLanguages | 1463 | 37 / 249 | 1.4K |
| GermanLanguages | 1451 | 53 / 261 | 744 |
| FrenchLanguages | 1471 | 47 / 252 | 1.6K |
| JapaneseLanguages | 1443 | 36 / 236 | 500 |
| WebDevLMArena | 1509 | 60 / 124 | 10.2K |
| VisionLMArena | 1282 | 34 / 146 | 16.4K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare Kimi K2.6
Moonshot AI
The lab behind Kimi, known for long-context and agentic open-weight models. Founded 2023, based in Beijing. moonshot.ai
Questions
Who makes Kimi K2.6?
Kimi K2.6 is made by Moonshot AI, founded 2023 and based in Beijing.
How much does Kimi K2.6 cost?
$0.65 per million input tokens and $3.41 per million output tokens, at its provider’s list price.
What is Kimi K2.6’s context window?
256K tokens (262,144).
How does Kimi K2.6 rank?
#44 of 351 on LMArena’s text leaderboard, rated 1455 (95% interval 1451–1460) from 40,026 votes, as of Oct 22, 2026.
Is Kimi K2.6 open source?
Kimi K2.6 has open weights under the Modified MIT license, downloadable from Hugging Face (moonshotai/Kimi-K2.6).