Kimi K2.7 Code kimi-k2.7-code
moonshotai · kimi coding flagship agentic
#8 overall
- params
- 1059B (A32B)
- arch
- moe
- context
- 256k
- license
- modified-mit open weights
- released
- Jun 2026
- reasoning
- yes
- downloads/30d
- 870.0k
# why ranked
Overall: #8 — score 44.2 ● medium — one signal missing, weights renormalized
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.50 | 41.9 |
| arena_elo | 0.30 | — |
| bench_composite | 0.20 | 50.0 |
missing signals are dropped and the remaining weights renormalized — never imputed.
Coding: provisional — score 93.1 ● low — a single signal; treat with caution
provisional: too few independent signals for a numbered position — the score is shown, but this model sorts after every ranked model.
| signal | weight | input (0–100) |
|---|---|---|
| aa_coding | 0.25 | 93.1 |
| aider_polyglot | 0.25 | — |
| arena_elo_code | 0.15 | — |
| swe_bench_verified | 0.35 | — |
missing signals are dropped and the remaining weights renormalized — never imputed.
# trend
collecting history — trends appear after a few daily runs.
# benchmarks
| benchmark | score | source | date |
|---|---|---|---|
| AA Coding Index | 60.8 | Artificial Analysis | — |
| AA Intelligence Index | 41.9 | Artificial Analysis | — |
| LiveBench Agentic Coding | 45.7 | LiveBench | Jun 2026 |
| LiveBench Coding | 74.0 | LiveBench | Jun 2026 |
| LiveBench Data Analysis | 62.7 | LiveBench | Jun 2026 |
| LiveBench IF | 56.3 | LiveBench | Jun 2026 |
| LiveBench Language | 77.9 | LiveBench | Jun 2026 |
| LiveBench Mathematics | 79.6 | LiveBench | Jun 2026 |
| LiveBench Reasoning | 82.8 | LiveBench | Jun 2026 |
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M blend | tps | uptime |
|---|---|---|---|---|---|---|---|
| Inceptron | int4 | 256k | $0.75 | $3.15 | $1.35 | — | 99.7% |
| DeepInfra | fp4 | 256k | $0.74 | $3.50 | $1.43 | — | — |
| Parasail | int4 | 256k | $0.75 | $3.50 | $1.44 | — | 97.9% |
| Venice | int4 | 250k | $0.75 | $3.50 | $1.44 | — | 100.0% |
| Ambient | int4 | 256k | $0.90 | $3.83 | $1.63 | — | 99.4% |
| Novita | int4 | 256k | $0.91 | $3.84 | $1.64 | — | 100.0% |
| ModelRun | fp4 | 256k | $0.92 | $4.00 | $1.69 | — | 100.0% |
| SiliconFlow | fp8 | 256k | $0.94 | $4.00 | $1.71 | — | 99.9% |
| AtlasCloud | int4 | 256k | $0.95 | $4.00 | $1.71 | — | 100.0% |
| Cloudflare | unknown | 256k | $0.95 | $4.00 | $1.71 | — | 100.0% |
| Moonshot AI | int4 | 256k | $0.95 | $4.00 | $1.71 | — | 100.0% |
| Together | unknown | 256k | $0.95 | $4.00 | $1.71 | — | — |
| Moonshot AI | int4 | 256k | $1.90 | $8.00 | $3.42 | — | 100.0% |
blended = (3·input + output) / 4 per 1M tokens · cheapest first
source aliases
- aa
kimi-k2.7-code- openrouter
moonshotai/kimi-k2.7-code