Compare · ModelsLive · 2 picked · head to head
GPT-6.1 Terra vs GPT-6 Astra
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-6 Astra wins on 8/11 benchmarks
GPT-6 Astra wins 8 of 11 shared benchmarks. Leads in general · math · knowledge.
Category leads
agentic·GPT-6.1 Terrageneral·GPT-6 Astramath·GPT-6 Astraknowledge·GPT-6 Astra
Hype vs Reality
Attention vs performance
GPT-6.1 Terra
#14 by perf·#2 by attention
GPT-6 Astra
#9 by perf·#2 by attention
Best value
GPT-6.1 Terra
9.7x better value than GPT-6 Astra
GPT-6.1 Terra
24.2 pts/$
$3.00/M
GPT-6 Astra
2.5 pts/$
$30.00/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
11 benchmarks · 2 models
GPT-6.1 TerraGPT-6 Astra
APEX-Agents
GPT-6.1 Terra leads by +3.6
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
GPT-6.1 Terra
68.3
GPT-6 Astra
64.7
Ebr Bench
GPT-6.1 Terra leads by +1.9
GPT-6.1 Terra
78.1
GPT-6 Astra
76.2
FrontierMath-Tier-4-v2-Private
GPT-6 Astra leads by +4.9
GPT-6.1 Terra
92.7
GPT-6 Astra
97.6
FrontierMath-Tiers-1-3-v2-Private
GPT-6 Astra leads by +3.0
GPT-6.1 Terra
95.7
GPT-6 Astra
98.6
Furniture Assembly
GPT-6 Astra leads by +1.2
GPT-6.1 Terra
70.2
GPT-6 Astra
71.4
GPQA diamond
GPT-6 Astra leads by +2.0
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-6.1 Terra
96.3
GPT-6 Astra
98.3
Mystery Game Puzzles
GPT-6 Astra leads by +11.0
GPT-6.1 Terra
71.4
GPT-6 Astra
82.4
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-6.1 Terra
100.0
GPT-6 Astra
100.0
SimpleQA Verified
GPT-6 Astra leads by +18.3
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
GPT-6.1 Terra
57.3
GPT-6 Astra
75.6
SpireClimb
GPT-6 Astra leads by +11.7
GPT-6.1 Terra
22.3
GPT-6 Astra
34.0
WeirdML v3
GPT-6 Astra leads by +15.1
GPT-6.1 Terra
44.9
GPT-6 Astra
60.0
Full benchmark table
| Benchmark | GPT-6.1 Terra | GPT-6 Astra |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 68.3 | 64.7 |
Ebr Bench | 78.1 | 76.2 |
FrontierMath-Tier-4-v2-Private | 92.7 | 97.6 |
FrontierMath-Tiers-1-3-v2-Private | 95.7 | 98.6 |
Furniture Assembly | 70.2 | 71.4 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 96.3 | 98.3 |
Mystery Game Puzzles | 71.4 | 82.4 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 100.0 | 100.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 57.3 | 75.6 |
SpireClimb | 22.3 | 34.0 |
WeirdML v3 | 44.9 | 60.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.00 | $5.00 | 1.1M tokens (~525 books) | $20.00 | |
| $10.00 | $50.00 | 1.1M tokens (~525 books) | $200.00 |