Compare · ModelsLive · 3 picked · head to head
GPT-6.1 Sol vs 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 16/28 benchmarks
GPT-6 Astra wins 16 of 28 shared benchmarks. Leads in general · knowledge · reasoning.
Category leads
agentic·GPT-6.1 Terrageneral·GPT-6 Astramath·GPT-6.1 Solknowledge·GPT-6 Astracoding·GPT-6.1 Terrareasoning·GPT-6 Astraspeed·GPT-6 Astra
Hype vs Reality
Attention vs performance
GPT-6.1 Sol
#10 by perf·#2 by attention
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
1.9x better value than GPT-6.1 Sol
GPT-6.1 Sol
12.5 pts/$
$6.00/M
GPT-6.1 Terra
24.1 pts/$
$3.00/M
GPT-6 Astra
2.5 pts/$
$30.00/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
OpenAI
$840.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
28 benchmarks · 3 models
GPT-6.1 SolGPT-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 Sol
60.0
GPT-6.1 Terra
68.3
GPT-6 Astra
64.7
Ebr Bench
GPT-6.1 Terra leads by +1.9
GPT-6.1 Sol
54.3
GPT-6.1 Terra
78.1
GPT-6 Astra
76.2
FrontierMath-Tier-4-v2-Private
GPT-6.1 Sol leads by +2.4
GPT-6.1 Sol
100.0
GPT-6.1 Terra
92.7
GPT-6 Astra
97.6
FrontierMath-Tiers-1-3-v2-Private
GPT-6.1 Sol
98.6
GPT-6.1 Terra
95.7
GPT-6 Astra
98.6
Furniture Assembly
GPT-6.1 Sol
71.4
GPT-6.1 Terra
70.2
GPT-6 Astra
71.4
GPQA diamond
GPT-6 Astra leads by +0.5
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 Sol
97.8
GPT-6.1 Terra
96.3
GPT-6 Astra
98.3
Mirrorcode
GPT-6.1 Terra leads by +15.6
GPT-6.1 Sol
61.1
GPT-6.1 Terra
76.7
GPT-6 Astra
60.0
Mystery Game Puzzles
GPT-6 Astra leads by +4.4
GPT-6.1 Sol
78.0
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 Sol
100.0
GPT-6.1 Terra
100.0
GPT-6 Astra
100.0
SimpleBench
GPT-6 Astra leads by +4.3
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
GPT-6.1 Sol
79.5
GPT-6.1 Terra
66.6
GPT-6 Astra
83.8
SimpleQA Verified
GPT-6 Astra leads by +1.7
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
GPT-6.1 Sol
73.9
GPT-6.1 Terra
57.3
GPT-6 Astra
75.6
SpireClimb
GPT-6 Astra leads by +10.2
GPT-6.1 Sol
23.8
GPT-6.1 Terra
22.3
GPT-6 Astra
34.0
WeirdML v3
GPT-6 Astra leads by +3.8
GPT-6.1 Sol
56.2
GPT-6.1 Terra
44.9
GPT-6 Astra
60.0
Artificial Analysis · CritPt
GPT-6.1 Sol
31.7
GPT-6 Astra
31.7
Artificial Analysis · GDPval
GPT-6.1 Sol leads by +1.1
GPT-6.1 Sol
54.7
GPT-6 Astra
53.6
Artificial Analysis · Humanity's Last Exam
GPT-6 Astra leads by +1.8
GPT-6.1 Sol
52.9
GPT-6 Astra
54.7
Artificial Analysis · Long Context Reasoning
GPT-6.1 Sol leads by +2.3
GPT-6.1 Sol
83.0
GPT-6 Astra
80.7
Artificial Analysis · MMMU Pro
GPT-6 Astra leads by +0.9
GPT-6.1 Sol
86.0
GPT-6 Astra
86.9
Artificial Analysis · Quality Index
GPT-6 Astra leads by +0.8
GPT-6.1 Sol
51.8
GPT-6 Astra
52.7
Artificial Analysis · SciCode
GPT-6 Astra leads by +2.3
GPT-6.1 Sol
54.2
GPT-6 Astra
56.5
ARC-AGI
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
GPT-6.1 Sol
98.5
GPT-6 Astra
98.5
ARC-AGI-2
GPT-6 Astra leads by +0.8
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
GPT-6.1 Sol
94.2
GPT-6 Astra
95.0
Chess Puzzles
GPT-6 Astra leads by +8.4
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
GPT-6.1 Sol
66.3
GPT-6 Astra
74.8
Dtbench
GPT-6 Astra leads by +1.3
GPT-6.1 Sol
94.2
GPT-6 Astra
95.5
Frontiercode
GPT-6 Astra leads by +3.0
GPT-6.1 Sol
50.2
GPT-6 Astra
53.3
Lmca
GPT-6 Astra leads by +1.9
GPT-6.1 Sol
73.9
GPT-6 Astra
75.7
PostTrainBench
GPT-6 Astra leads by +3.1
GPT-6.1 Sol
38.8
GPT-6 Astra
41.9
Proofbench
GPT-6.1 Sol
99.0
GPT-6 Astra
99.0
Full benchmark table
| Benchmark | GPT-6.1 Sol | 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. | 60.0 | 68.3 | 64.7 |
Ebr Bench | 54.3 | 78.1 | 76.2 |
FrontierMath-Tier-4-v2-Private | 100.0 | 92.7 | 97.6 |
FrontierMath-Tiers-1-3-v2-Private | 98.6 | 95.7 | 98.6 |
Furniture Assembly | 71.4 | 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. | 97.8 | 96.3 | 98.3 |
Mirrorcode | 61.1 | 76.7 | 60.0 |
Mystery Game Puzzles | 78.0 | 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 | 100.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 79.5 | 66.6 | 83.8 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 73.9 | 57.3 | 75.6 |
SpireClimb | 23.8 | 22.3 | 34.0 |
WeirdML v3 | 56.2 | 44.9 | 60.0 |
Artificial Analysis · CritPt | 31.7 | n/a | 31.7 |
Artificial Analysis · GDPval | 54.7 | n/a | 53.6 |
Artificial Analysis · Humanity's Last Exam | 52.9 | n/a | 54.7 |
Artificial Analysis · Long Context Reasoning | 83.0 | n/a | 80.7 |
Artificial Analysis · MMMU Pro | 86.0 | n/a | 86.9 |
Artificial Analysis · Quality Index | 51.8 | n/a | 52.7 |
Artificial Analysis · SciCode | 54.2 | n/a | 56.5 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 98.5 | n/a | 98.5 |
ARC-AGI-2 ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data. | 94.2 | n/a | 95.0 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 66.3 | n/a | 74.8 |
Dtbench | 94.2 | n/a | 95.5 |
Frontiercode | 50.2 | n/a | 53.3 |
Lmca | 73.9 | n/a | 75.7 |
PostTrainBench | 38.8 | n/a | 41.9 |
Proofbench | 99.0 | n/a | 99.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $2.00 | $10.00 | 1.1M tokens (~525 books) | $40.00 | |
| $1.00 | $5.00 | 1.1M tokens (~525 books) | $20.00 | |
| $10.00 | $50.00 | 1.1M tokens (~525 books) | $200.00 |