Kimi K2 Thinking kimi-k2-thinking
moonshotai · kimi reasoning flagship agentic
#6 overall #16 coding #6 agentic
- params
- 1000B (A32B)
- arch
- moe
- context
- 256k
- license
- modified-mit open weights
- released
- Nov 2025
- reasoning
- yes
- train compute
- 4.2e+24 FLOP
- downloads/30d
- 139.7k
# why ranked
Overall: #6 — score 32.7 ● low — a single signal; treat with caution
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.50 | 32.7 |
| arena_elo | 0.30 | — |
| bench_composite | 0.20 | — |
missing signals are dropped and the remaining weights renormalized — never imputed.
Coding: #16 — score 61.5 ● low — a single signal; treat with caution
| signal | weight | input (0–100) |
|---|---|---|
| aa_coding | 0.25 | — |
| aider_polyglot | 0.25 | — |
| arena_elo_code | 0.15 | — |
| swe_bench_verified | 0.35 | 61.5 |
missing signals are dropped and the remaining weights renormalized — never imputed.
Agentic: #6 — score 61.5 ● low — a single signal; treat with caution
| signal | weight | input (0–100) |
|---|---|---|
| swe_bench_verified | 1.00 | 61.5 |
# trend
# benchmarks
| benchmark | score | source | date |
|---|---|---|---|
| AA Intelligence Index | 32.7 | Artificial Analysis | — |
| AA Math Index | 94.7 | Artificial Analysis | — |
| SWE-bench Verified | 63.4 | SWE-bench | Dec 2025 |
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M blend | tps | uptime |
|---|---|---|---|---|---|---|---|
| unknown | 256k | $0.60 | $2.50 | $1.07 | — | 100.0% | |
| Novita | bf16 | 256k | $0.60 | $2.50 | $1.07 | — | — |
blended = (3·input + output) / 4 per 1M tokens · cheapest first
source aliases
- aa
kimi-k2-thinking- arena
Kimi-K2-Thinking- epoch
Kimi K2 Thinking- openrouter
moonshotai/kimi-k2-thinking