GPT-6.1 Sol vs GPT-6.1 Terra
| Spec | GPT-6.1 Sol | GPT-6.1 Terra |
|---|---|---|
| Respan Index | 69.8 (#7) | 68.9 (#9) |
| Blended price per 1M | $2 | $1 |
| Context window | 1.1M | 1.1M |
| Input / output per 1M | $1 / $5 | $0.5 / $2.5 |
| Max output | 128K | 128K |
| Input | text, vision | text, vision |
| Released | 2026-09-29 | 2026-10-26 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | GPT-6.1 Sol | GPT-6.1 Terra |
|---|---|---|
| Coding | 53.3 GPT-6.1 Sol | 57.9 GPT-6.1 Terra |
| Agents | 73.1 GPT-6.1 Sol | 77.0 GPT-6.1 Terra |
| Reasoning | 87.2 GPT-6.1 Sol | 83.0 GPT-6.1 Terra |
| Knowledge & language | 74.4 GPT-6.1 Sol | 57.4 GPT-6.1 Terra |
| Human preference | 59.8 GPT-6.1 Sol | 57.9 GPT-6.1 Terra |
Benchmarks both report
GPT-6.1 Sol leads on 9 of the 12 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GPT-6.1 Sol | GPT-6.1 Terra |
|---|---|---|
| LMArena Agent (LMArena) | 0.1247 | 0.1057 |
| LMArena WebDev (LMArena) | 1751 | 1673 |
| APEX-Agents (Mercor) | 60% | 68.3% |
| EBR-bench (Epoch AI) | 54.3% | 78.1% |
| FrontierMath Tier 4 v2 (Epoch AI) | 100% | 92.7% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 93.7% | 90.9% |
| Furniture Assembly (Epoch AI) | 80% | 79.2% |
| GPQA Diamond | 95.4% | 94.3% |
| Mystery Game Puzzles (Epoch AI) | 80% | 74% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 100% |
| SimpleQA Verified | 73.9% | 57.3% |
| Terminal-Bench 4.0 (Vals AI) | 55.1% | 49.5% |
FAQ
Is GPT-6.1 Sol better than GPT-6.1 Terra?
GPT-6.1 Sol scores 69.8 on the Respan Index (#7), ahead of GPT-6.1 Terra at 68.9 (#9). GPT-6.1 Sol leads on 9 of the 12 benchmarks both report.
Which is cheaper, GPT-6.1 Sol or GPT-6.1 Terra?
GPT-6.1 Sol lists at $1 input and $5 output per 1M tokens; GPT-6.1 Terra at $0.5 and $2.5. GPT-6.1 Terra is 2.0x cheaper per token at list price.
Which has the larger context window?
Both accept 1.1M tokens of context.