Compare · ModelsLive · 2 picked · head to head
Claude Opus 5 vs GPT-6.1 Terra
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-6.1 Terra wins on 9/10 benchmarks
GPT-6.1 Terra wins 9 of 10 shared benchmarks. Leads in agentic · general · math.
Category leads
agentic·GPT-6.1 Terrageneral·GPT-6.1 Terramath·GPT-6.1 Terraknowledge·GPT-6.1 Terra
Hype vs Reality
Attention vs performance
Claude Opus 5
#23 by perf·#5 by attention
GPT-6.1 Terra
#14 by perf·#2 by attention
Best value
GPT-6.1 Terra
5.2x better value than Claude Opus 5
Claude Opus 5
4.6 pts/$
$15.00/M
GPT-6.1 Terra
24.2 pts/$
$3.00/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
10 benchmarks · 2 models
Claude Opus 5GPT-6.1 Terra
APEX-Agents
GPT-6.1 Terra leads by +2.5
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Claude Opus 5
65.8
GPT-6.1 Terra
68.3
Ebr Bench
GPT-6.1 Terra leads by +32.4
Claude Opus 5
45.7
GPT-6.1 Terra
78.1
FrontierMath-Tier-4-v2-Private
GPT-6.1 Terra leads by +19.5
Claude Opus 5
73.2
GPT-6.1 Terra
92.7
FrontierMath-Tiers-1-3-v2-Private
GPT-6.1 Terra leads by +5.5
Claude Opus 5
90.1
GPT-6.1 Terra
95.7
Furniture Assembly
GPT-6.1 Terra leads by +26.2
Claude Opus 5
44.0
GPT-6.1 Terra
70.2
GPQA diamond
GPT-6.1 Terra leads by +0.6
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Opus 5
95.7
GPT-6.1 Terra
96.3
Mystery Game Puzzles
GPT-6.1 Terra leads by +16.5
Claude Opus 5
54.8
GPT-6.1 Terra
71.4
OTIS Mock AIME 2024-2025
GPT-6.1 Terra leads by +1.1
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Opus 5
98.9
GPT-6.1 Terra
100.0
SimpleQA Verified
Claude Opus 5 leads by +2.6
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Opus 5
59.9
GPT-6.1 Terra
57.3
WeirdML v3
GPT-6.1 Terra leads by +8.8
Claude Opus 5
36.1
GPT-6.1 Terra
44.9
Full benchmark table
| Benchmark | Claude Opus 5 | GPT-6.1 Terra |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 65.8 | 68.3 |
Ebr Bench | 45.7 | 78.1 |
FrontierMath-Tier-4-v2-Private | 73.2 | 92.7 |
FrontierMath-Tiers-1-3-v2-Private | 90.1 | 95.7 |
Furniture Assembly | 44.0 | 70.2 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 95.7 | 96.3 |
Mystery Game Puzzles | 54.8 | 71.4 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 98.9 | 100.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 59.9 | 57.3 |
WeirdML v3 | 36.1 | 44.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $5.00 | $25.00 | 1.0M tokens (~500 books) | $100.00 | |
| $1.00 | $5.00 | 1.1M tokens (~525 books) | $20.00 |