Qwen3.8 27B vs K2-V2: Release Comparison
Comparison of the Qwen3.8 27B and K2-V2 releases: 4 and 3 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 7 models.
- For intelligence, Qwen3.8 27B scores highest: Qwen3.8 27B (xhigh) at 34, against K2-V2 (high) at 10 for K2-V2.
Releases compared
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost per Task (USD, Log Scale)
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indexes
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better
Further details
Input modality | Output modality | Weights | Provider Benchmarks | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 27B (xhigh) |  Alibaba | 34 | 34 | 37 | 35 | 34 | 33 | 43 | $0.82 | $0.4 | $0.50 | $3.00 | $0.05 | $1,170 | 67k | 48k | 198M | 41 | 4.03s | 52.50s | 64.62s | 1315.67s | 27B | 256k | Aug 2026 | - | Yes | Supports: text, image, and video | Supports: text |   +2 | |||
| Qwen3.8 27B (medium) | Alibaba | 28 | 28 | 34 | 27 | - | 25 | 31 | $0.90 | $0.4 | $0.50 | $3.00 | $0.05 | $977 | 52k | 32k | 113M | 50 | 3.87s | 43.82s | 53.81s | 999.15s | 27B | 256k | Aug 2026 | - | Yes | Supports: text, image, and video | Supports: text |  | |||
| Qwen3.8 27B (low) | Alibaba | 26 | 27 | 29 | 28 | - | 24 | 32 | $0.83 | $0.4 | $0.50 | $3.00 | $0.05 | $876 | 45k | 26k | 82M | 51 | 3.82s | 43.04s | 52.85s | 826.49s | 27B | 256k | Aug 2026 | - | Yes | Supports: text, image, and video | Supports: text | | |||
| Qwen3.8 27B (Non-reasoning) | Alibaba | 20 | 19 | 16 | 22 | - | 22 | 30 | $1.91 | $0.4 | $0.50 | $3.00 | $0.05 | $1,570 | 30k | 0 | 43M | 49 | 3.87s | 3.87s | 14.06s | 560.61s | 27B | 256k | Aug 2026 | - | No | Supports: text, image, and video | Supports: text | | |||
| K2-V2 (high) |  Institute of Foundation Models | 10 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 70B | 512k | Dec 2025 | - | Yes | Supports: text | Supports: text | - | |||
| K2-V2 (medium) | Institute of Foundation Models | 9 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 70B | 512k | Dec 2025 | - | Yes | Supports: text | Supports: text | - | |||
| K2-V2 (low) | Institute of Foundation Models | 7 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 70B | 512k | Dec 2025 | - | Yes | Supports: text | Supports: text | - | |||