GPT-6 Astra vs Gemma 4 12B: Release Comparison
Comparison of the GPT-6 Astra and Gemma 4 12B releases: 5 and 2 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 Gemma 4 12B (Reasoning) at 14 for Gemma 4 12B.
- For output speed, Gemma 4 12B is fastest: Gemma 4 12B (Non-reasoning) at 118 t/s, against GPT-6 Astra (max) at 52 t/s 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 | 52 | 352.15s | 352.15s | 361.67s | 525.19s | - | 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 | 51 | 198.11s | 198.11s | 207.87s | 329.89s | - | 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 | 49 | 73.16s | 73.16s | 83.42s | 242.90s | - | 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 | 45 | 5.86s | 5.86s | 16.93s | 211.71s | - | 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 | 45 | 3.03s | 3.03s | 14.06s | 97.93s | - | 1M | Sep 2026 | Apr 2026 | Yes | Supports: text and image | Supports: text | Not available | - | | |
| Gemma 4 12B (Reasoning) |  Google | 14 | - | - | - | - | - | - | - | $0.1 | $0.10 | $0.30 | - | - | - | - | - | 113 | 2.35s | 20.08s | 24.51s | - | 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 | - | - | - | - | - | 118 | 2.34s | 2.34s | 6.58s | - | 12B | 262k | Jun 2026 | - | No | Supports: text, image, speech, and video | Supports: text | | |||