GPT-5.4 vs GPT-6.1 Terra
| Spec | GPT-5.4 | GPT-6.1 Terra |
|---|---|---|
| Respan Index | 49.9 (#44) | 69.1 (#14) |
| Blended price per 1M | $5.63 | $2 |
| Context window | 1.1M | 1.1M |
| Input / output per 1M | $2.5 / $15 | $1 / $5 |
| Max output | 128K | 128K |
| Input | text, vision | text, vision |
| Released | 2026-03-05 | 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-5.4 | GPT-6.1 Terra |
|---|---|---|
| Coding | 25.9 GPT-5.4 | 57.9 GPT-6.1 Terra |
| Agents | 61.9 GPT-5.4 | 77.5 GPT-6.1 Terra |
| Reasoning | 61.4 GPT-5.4 | 82.9 GPT-6.1 Terra |
| Knowledge & language | 46.9 GPT-5.4 | 57.5 GPT-6.1 Terra |
| Human preference | 52.9 GPT-5.4 | 58.2 GPT-6.1 Terra |
Benchmarks both report
GPT-6.1 Terra leads on 13 of the 15 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GPT-5.4 | GPT-6.1 Terra |
|---|---|---|
| LMArena Elo | 1475 | 1474 |
| LMArena Vision (LMArena) | 1282 | 1263 |
| LMArena WebDev (LMArena) | 1462 | 1684 |
| MirrorCode (Epoch AI) | 23.3% | 76.7% |
| LMArena Agent (LMArena) | 0.0267 | 0.1048 |
| APEX-Agents (Mercor) | 52.4% | 68.3% |
| EBR-bench (Epoch AI) | 25.4% | 78.1% |
| FrontierMath Tier 4 v2 (Epoch AI) | 49% | 92.7% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 78.6% | 90.9% |
| Furniture Assembly (Epoch AI) | 37.5% | 79.2% |
| GPQA Diamond | 92.8% | 94.3% |
| Mystery Game Puzzles (Epoch AI) | 37% | 74% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 97.8% | 100% |
| SimpleQA Verified | 45.1% | 57.3% |
| Vending-Bench 2 (Andon Labs) | 6144.18 | 9107.46 |
FAQ
Is GPT-5.4 better than GPT-6.1 Terra?
GPT-6.1 Terra scores 69.1 on the Respan Index (#14), ahead of GPT-5.4 at 49.9 (#44). GPT-6.1 Terra leads on 13 of the 15 benchmarks both report.
Which is cheaper, GPT-5.4 or GPT-6.1 Terra?
GPT-5.4 lists at $2.5 input and $15 output per 1M tokens; GPT-6.1 Terra at $1 and $5. GPT-6.1 Terra is 2.8x cheaper per token at list price.
Which has the larger context window?
Both accept 1.1M tokens of context.
Compare other models
- vsGPT-5.4 vs GPT-5.2
- vsGPT-5.5 vs GPT-5.4
- vsGPT-6.1 Terra vs GPT-5.6 Terra
- vsGPT-6.1 Sol vs GPT-5.4
- vsClaude Fable 5.2 vs GPT-6.1 Terra
- vsGPT-5.4 vs Claude Opus 4.7
- vsGPT-5.4 vs DeepSeek V4 Pro
- vsGPT-5.4 vs GPT-5.4 Pro
- vsGPT-6.1 Terra vs Gemini 4 Argon
- vsGPT-6.1 Terra vs GPT-6.2 Sol
- vsGPT-6.1 Terra vs GPT-6.1 Sol