- Intelligence
- 25.8
- Rank 166 of 744 measured models
- Coding
- 60.8
- Rank 83 of 298 measured models
- Output speed
- 58.2 t/s
- Rank 286 of 403 measured models
- Price/1M
- $1.71
- Rank 451 of 659 measured models
- Context window
- 256K
- Rank 518 of 1199 measured models
- Cost per task
- $0.541
- Rank 108 of 193 measured models
Kimi K2.7 Code scores 25.8 on the Artificial Analysis Intelligence Index, ranking 166th of 744 measured models. The closest models on this index are GPT-5.5 Instant (June 2026) (26.0), Grok 4.20 0309 v2 (25.7), and Inkling Small (25.7). At $1.71 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5.5 Instant (June 2026) ($11.25), more expensive than Grok 4.20 0309 v2 ($1.56) and Inkling Small ($0.525). With an output speed of 58.2 t/s, it is slower than GPT-5.5 Instant (June 2026) (151 t/s), Grok 4.20 0309 v2 (101 t/s), and Inkling Small (190 t/s).
Additional benchmarks16
Design Arena · 3d50.3%
Design Arena · Agenticgamedev43.0%
Design Arena · Androidnative46.0%
Design Arena · Asciiart48.4%
Design Arena · Codecategories50.0%
Design Arena · Dataviz48.6%
Design Arena · Fullstack50.9%
Design Arena · Gamedev47.1%
Design Arena · Godotgamedev49.2%
Design Arena · Htmlslides53.6%
Design Arena · Mobileapps46.3%
Design Arena · Python Pptxslides44.7%
Design Arena · Svg44.4%
Design Arena · Uicomponent50.8%
Design Arena · Webapps46.9%
Design Arena · Website51.4%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GPT-5.5 Instant (June 2026)
OpenAI · $11.25 · 151 t/s
26.0+0.2$11.25151 t/sCompare - MiMo-V2.5-Pro
Xiaomi · $0.544 · 38.8 t/s
26.0+0.2$0.54438.8 t/sCompare - Grok 4.20 0309 v2
SpaceXSI · $1.56 · 101 t/s
25.7−0.1$1.56101 t/sCompare - Inkling Small
Thinking Machines · $0.525 · 190 t/s
25.7−0.1$0.525190 t/sCompare
