DeepSeek V4.1 Flash vs GPT-6 Astra: Release Comparison
Comparison of the DeepSeek V4.1 Flash and GPT-6 Astra releases: 2 and 5 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 7 models.
- For intelligence, GPT-6 Astra scores highest: GPT-6 Astra (max) at 53, against DeepSeek V4.1 Flash (Reasoning, Max Effort) at 39 for DeepSeek V4.1 Flash.
- For output speed, DeepSeek V4.1 Flash is fastest: DeepSeek V4.1 Flash (Non-Reasoning) at 243 t/s, against GPT-6 Astra (max) at 54 t/s for GPT-6 Astra.
- For cost per task, DeepSeek V4.1 Flash is cheapest: DeepSeek V4.1 Flash (Non-Reasoning) at $0.15, against GPT-6 Astra (low) at $0.82 for GPT-6 Astra.
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 | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-6 Astra (max) |  OpenAI | 53 | 55 | 57 | 59 | 52 | 55 | 60 | $3.26 | $7.7 | $10.00 | $50.00 | $1.00 | $5,324 | 27k | 17k | 60M | 54 | 361.32s | 361.32s | 370.62s | 514.56s | - | 1M | Sep 2026 | Apr 2026 | Yes | Supports: text and image | Supports: text | Not available | - |   | |
| GPT-6 Astra (xhigh) | OpenAI | 52 | 54 | 57 | 58 | - | 55 | 59 | $2.31 | $7.7 | $10.00 | $50.00 | $1.00 | $3,803 | 17k | 9k | 38M | 53 | 184.48s | 184.48s | 193.92s | 317.53s | - | 1M | Sep 2026 | Apr 2026 | Yes | Supports: text and image | Supports: text | Not available | - | | |
| GPT-6 Astra (high) | OpenAI | 51 | 53 | 55 | 58 | - | 53 | 58 | $1.73 | $7.7 | $10.00 | $50.00 | $1.00 | $2,925 | 12k | 5k | 26M | 52 | 66.16s | 66.16s | 75.76s | 230.16s | - | 1M | Sep 2026 | Apr 2026 | Yes | Supports: text and image | Supports: text | Not available | - | | |
| GPT-6 Astra (medium) | OpenAI | 50 | 52 | 54 | 57 | - | 52 | 58 | $1.54 | $7.7 | $10.00 | $50.00 | $1.00 | $2,434 | 10k | 3k | 19M | 48 | 6.37s | 6.37s | 16.71s | 198.96s | - | 1M | Sep 2026 | Apr 2026 | Yes | Supports: text and image | Supports: text | Not available | - | | |
| GPT-6 Astra (low) | OpenAI | 46 | 49 | 50 | 53 | - | 48 | 55 | $0.82 | $7.7 | $10.00 | $50.00 | $1.00 | $1,537 | 4k | 938 | 10M | 46 | 3.29s | 3.29s | 14.06s | 97.18s | - | 1M | Sep 2026 | Apr 2026 | Yes | Supports: text and image | Supports: text | Not available | - | | |
| DeepSeek V4.1 Flash (Reasoning, Max Effort) |  DeepSeek | 39 | 45 | 52 | 41 | 41 | 39 | 44 | $0.27 | $0.2 | $0.30 | $1.20 | $0.006 | $477 | 89k | 63k | 253M | 232 | 0.97s | 9.58s | 11.73s | 282.36s | 552B 16B active at inference time | 1M | Sep 2026 | - | Yes | Supports: text and image | Supports: text |    +15 | |||
| DeepSeek V4.1 Flash (Non-Reasoning) | DeepSeek | 25 | 30 | 36 | 30 | - | 25 | 32 | $0.15 | $0.2 | $0.30 | $1.20 | $0.006 | $156 | 34k | 0 | 45M | 243 | 1.16s | 1.16s | 3.22s | 136.49s | 552B 16B active at inference time | 1M | Sep 2026 | - | No | Supports: text and image | Supports: text | | |||