Kimi K2 0905
September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding
Shogo Agent Index
Estimated#80 of 9225.3range 16.2–34.3 · 12% of weight measured
Agentic coding
26
34% measured
Long-horizon autonomy
34
estimated
Knowledge-work agents
21
estimated
Computer use
13
estimated
Security & context learning
25
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 60 | |
| Terminal-Bench 2.0 | 27.8% | 8% | Terminus 2 | |
| DeepSWE | est. | 6% | predicted 17 | |
| FrontierSWE | est. | 5% | predicted 2 | |
| CursorBench | est. | 4% | predicted 22 | |
| GSO-Bench | 4.9% | 4% | OpenHands | |
| METR Time Horizons | est. | 10% | predicted 59 | |
| Vending-Bench 2 | est. | 6% | predicted 7 | |
| PostTrainBench | est. | 4% | predicted 15 | |
| APEX-Agents | est. | 8% | predicted 18 | |
| GDPval | est. | 7% | predicted 24 | |
| Remote Labor Index | est. | 5% | predicted 1 | |
| DeepResearch Bench | est. | 5% | predicted 43 | |
| OSWorld 2.0 | est. | 6% | predicted 1 | |
| OSWorld | est. | 4% | predicted 31 | |
| Cybench | est. | 5% | predicted 35 | |
| CL-bench | est. | 5% | predicted 15 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| Aider Polyglot | Coding | 59.1% | source |
| Fiction.LiveBench | Long context | 66.7% | source |
| SimpleBench | Reasoning | 26.3% | source |
API hosts
Live prices and uptime for every host serving Kimi K2 0905 via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| Novita | $0.60 | $2.50 | — | $0.69 | 100.0% | fp8 |