DeepSeek V4 Flash 0731 vs Gemma 4 12B: Release Comparison
Comparison of the DeepSeek V4 Flash 0731 and Gemma 4 12B releases: 2 and 2 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 4 models.
- For intelligence, DeepSeek V4 Flash 0731 scores highest: DeepSeek V4 Flash 0731 Vision (Reasoning, Max Effort) at 35, against Gemma 4 12B (Reasoning) at 14 for Gemma 4 12B.
- For output speed, DeepSeek V4 Flash 0731 is fastest: DeepSeek V4 Flash 0731 Vision (Reasoning, Max Effort) at 236 t/s, against Gemma 4 12B (Reasoning) at 112 t/s for Gemma 4 12B.
Releases compared
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 4.0 · 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 0731 Vision (Reasoning, Max Effort) |  DeepSeek | 35 | 38 | 44 | 37 | - | 35 | 40 | $0.31 | $0.2 | $0.44 | $1.32 | $0.014 | $445 | 69k | 46k | 170M | 236 | 1.14s | 9.64s | 11.76s | 222.63s | 284B 13B active at inference time | 1M | Aug 2026 | - | Yes | Supports: text and image | Supports: text | Not available | - |  | |
| DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | DeepSeek | 35 | 38 | 43 | 38 | 35 | 35 | 40 | $0.22 | $0.2 | $0.44 | $1.32 | $0.014 | $474 | 62k | 45k | 242M | 227 | 1.49s | 10.30s | 12.50s | 211.11s | 284B 13B active at inference time | 1M | Jul 2026 | - | Yes | Supports: text | Supports: text |    +13 | |||
| Gemma 4 12B (Reasoning) |  Google | 14 | - | - | - | - | - | - | - | $0.1 | $0.10 | $0.30 | - | - | - | - | - | 112 | 2.42s | 20.30s | 24.76s | - | 12B | 256k | Jun 2026 | - | Yes | Supports: text, image, speech, and video | Supports: text |  | |||
| Gemma 4 12B (Non-reasoning) | Google | 9 | - | - | - | - | - | - | - | $0.1 | $0.10 | $0.30 | - | - | - | - | - | 106 | 2.40s | 2.40s | 7.10s | - | 12B | 262k | Jun 2026 | - | No | Supports: text, image, speech, and video | Supports: text | | |||