DeepSeek V4 Flash 0420 vs Hermes 4 - Llama-3.1 405B: Release Comparison
Comparison of the DeepSeek V4 Flash 0420 and Hermes 4 - Llama-3.1 405B releases: 3 and 2 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 5 models.
- For intelligence, DeepSeek V4 Flash 0420 scores highest: DeepSeek V4 Flash (Reasoning, High Effort) at 25, against Hermes 4 - Llama-3.1 405B (Reasoning) at 7 for Hermes 4 - Llama-3.1 405B.
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indices
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2, AA-Briefcase, Terminal-Bench v4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2, AA-Briefcase, AA-LCR v1.1 · Higher is better
Further details
Input modality | Output modality | Weights | Provider Benchmarks | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash (Reasoning, High Effort) |  DeepSeek | 25 | 29 | 29 | 29 | 26 | 26 | 34 | $0.19 | $0.1 | $0.13 | $0.28 | $0.028 | $210 | 42k | 26k | 128M | - | - | - | - | - | 284B 13B active at inference time | 1M | Apr 2026 | - | Yes | Supports: text | Supports: text |    +4 | |||
| DeepSeek V4 Flash (Reasoning, Max Effort) | DeepSeek | 25 | 28 | 28 | 28 | 27 | 27 | 33 | $0.12 | $0.1 | $0.13 | $0.28 | $0.028 | $191 | 55k | 41k | 250M | - | - | - | - | - | 284B 13B active at inference time | 1M | Apr 2026 | - | Yes | Supports: text | Supports: text |  +2 | |||
| DeepSeek V4 Flash (Non-reasoning) | DeepSeek | 19 | - | - | - | - | - | - | - | $0.1 | $0.0938 | $0.195 | $0.07 | - | - | - | - | - | - | - | - | - | 284B 13B active at inference time | 1M | Apr 2026 | - | No | Supports: text | Supports: text |  | |||
| Hermes 4 - Llama-3.1 405B (Reasoning) |  Nous Research | 7 | - | - | - | - | - | - | - | $1.2 | $1.00 | $3.00 | - | - | - | - | - | 44 | 2.52s | 48.45s | 59.94s | - | 406B | 128k | Aug 2025 | - | Yes | Supports: text | Supports: text |  | |||
| Hermes 4 - Llama-3.1 405B (Non-reasoning) | Nous Research | 7 | - | - | - | - | - | - | - | $1.2 | $1.00 | $3.00 | - | - | - | - | - | 43 | 2.39s | 2.39s | 13.95s | - | 406B | 128k | Aug 2025 | - | No | Supports: text | Supports: text | | |||