GPT-6.1 Terra
| Released | 2026-10-26 |
|---|---|
| Price per 1M | $1.00 in · $5.00 out |
| Overall score | 63.6 · rank 10 |
| Context window | 1,050,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 63.6 | 10 | 29 |
| Overall: Coding | 64.4 | 7 | 24 |
| Overall: Reasoning | 63.5 | 14 | 12 |
| Overall: Agentic work | 63.4 | 9 | 21 |
| Overall: Frontend | 63.2 | 8 | 7 |
| Coding | 66.1 | 4 | 4 |
| Agents | 62.2 | 13 | 10 |
| Reasoning | 63.6 | 21 | 7 |
| Math | 66.3 | 7 | 3 |
| Knowledge | 58.2 | 42 | 2 |
| Frontend | 61.8 | 13 | 3 |
| Value vs price | +13.8 | 12 |
Buzz
| Posts on X | About 68 a day |
|---|---|
| Mood | 25% positive, 5% negative |
| Hacker News | 5 mentions this week |
| Checked | 2026-11-11 |
- After the failed Fable 5.2, I started wondering: is the AI industry a fake and a scam? If you dig into the latest releases from AI labs, here's what you find: 1. In the five years since LLMs appeared, there has been no revolutionary leap in intelligence. It's the same transform…
- We ran Fable 5.2 through 100 unsaturated coding and engineering environments spanning spatial reasoning, planning, games, circuit design, and more. As with all Fable releases, it was an extremely expensive benchmark to run. The biggest winner, however, was OpenAI. Astra, GPT 6.…
- @Gegam245074 GPT 6.1 terra on max is fucking incredible and you are really fucking retarded, man. Delete your account.
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 66.7 ±3.0 | 9 |
| High | 58.7 ±4.9 | 3 |
| Low | 58.8 ±5.2 | 2 |
| Max | 63.1 ±1.8 | 18 |
| Medium | 59.2 ±5.2 | 2 |
| Non-reasoning | 53.5 ±5.2 | 2 |
| Extra High | 63.7 ±4.6 | 3 |
Evidence
Coding 66.1 ±4.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Coding | 89.2% | LiveBench | 2026-11-06 |
| WeirdML v3 | 28.1% | Epoch AI | 2026-11-11 |
| MirrorCode | 76.7% | Epoch AI | 2026-10-30 |
| SciCode | 55.1% | Epoch AI | 2026-11-11 |
Agents 62.2 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 49.5% | Vals AI | 2026-11-09 |
| APEX-Agents | 68.3% | Epoch AI | 2026-11-11 |
| LiveBench 2.0 Agentic | 56.2% | LiveBench | 2026-11-06 |
| LiveBench 2.0 Browser Use | 93.1% | LiveBench | 2026-11-06 |
| EMB v1.1 (Excel financial modeling) | 73.3% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Research | 79.1% | LiveBench | 2026-11-06 |
| Tax Agent Bench | 17.1% | Vals AI | 2026-11-09 |
| Finance Agent v2.1 | 56.0% | Vals AI | 2026-11-09 |
| Vending-Bench 2 | $9,107 | Epoch AI | 2026-11-11 |
| HLAB-Vals 1.1 (legal agent) | 1.7% | Vals AI | 2026-11-09 |
Reasoning 63.6 ±3.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 86.8% | Lech Mazur | 2026-11-10 |
| GPQA Diamond | 94.3% | Epoch AI | 2026-10-26 |
| CritPt | 28.0% | Epoch AI | 2026-11-11 |
| SimpleBench | 72.2% | SimpleBench | 2026-11-10 |
| LiveBench 2.0 Reasoning | 88.7% | LiveBench | 2026-11-06 |
| Mystery Game Puzzles | 74.0% | Epoch AI | 2026-10-26 |
| LiveBench 2.0 Data Analysis | 82.3% | LiveBench | 2026-11-06 |
Math 66.3 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 90.9% | Epoch AI | 2026-10-26 |
| FrontierMath Tier 4 | 92.7% | Epoch AI | 2026-10-26 |
| OTIS Mock AIME 2024-2025 | 100.0% | Epoch AI | 2026-10-26 |
Knowledge 58.2 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 57.3% | Epoch AI | 2026-10-26 |
| Legal Research Bench | 26.0% | Vals AI | 2026-11-09 |
Frontend 61.8 ±1.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Design | 79.7% | LiveBench | 2026-11-06 |
| Vibe Code Bench v1.1 | 84.0% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,679 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| CritPt | 26.6% | Epoch AI | A stronger configuration result was used |
| CritPt | 15.1% | Epoch AI | A stronger configuration result was used |
| CritPt | 21.4% | Epoch AI | A stronger configuration result was used |
| CritPt | 25.7% | Epoch AI | A stronger configuration result was used |
| CritPt | 4.9% | Epoch AI | A stronger configuration result was used |
| SciCode | 53.4% | Epoch AI | A stronger configuration result was used |
| SciCode | 52.4% | Epoch AI | A stronger configuration result was used |
| SciCode | 51.6% | Epoch AI | A stronger configuration result was used |
| SciCode | 51.6% | Epoch AI | A stronger configuration result was used |
| SciCode | 47.8% | Epoch AI | A stronger configuration result was used |
Names matched to this model
gpt-6-1-terra