GPT-6.1 Terra vs GPT-6 Sol
Full profiles: GPT-6.1 Terra (OpenAI) and GPT-6 Sol (OpenAI): every benchmark, price and rank.
Updated · Data from 9 sources
As of 27 Oct 2026, GPT-6.1 Terra (max) and GPT-6 Sol (max) are neck and neck on quality (65.9 vs 66.3 on the BenchLeader Index, inside the ±8.0 margin of error), and GPT-6.1 Terra (max) costs 2.0× less, which makes it the better buy for most workloads. GPT-6.1 Terra leads in every category we measure both in.
GPT-6.1 Terra benchmarks Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Reasoning | GPT-6.1 Terra | 86 vs 71 category score; CritPt 28.0% vs 30.9% | High |
| Knowledge | GPT-6.1 Terra | 75 vs 70 category score; AA-Omniscience 29.8 vs 27.1 | Medium |
| Long documents | Either | 66 vs 67 category score; AA-LCR 82.7% vs 83.7% | Either |
| Images and other media | GPT-6.1 Terra | 68 vs 61 category score; MMMU-Pro 84.7% vs 83.0% | Medium |
| Chat quality (human preference) | – | Only GPT-6 Sol has an Arena rating (65 category score) | Not comparable |
| Lowest cost | GPT-6.1 Terra | $2.00 vs $4.00 per 1M blended; agentic coding session $0.080 vs $0.160 | – |
| Fastest first answer | Either | 131.8 s (GPT-6.1 Terra (max)) vs 132.5 s (GPT-6 Sol (max)) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- GPT-6.1 Terra (max) and GPT-6 Sol (max) are neck and neck on quality (65.9 vs 66.3, within the ±8.0 margin).
- GPT-6.1 Terra (max) is stronger in composite, knowledge, multimodal, reasoning.
- GPT-6 Sol (max) is stronger in long context, agents & tools, coding, human preference, maths.
- GPT-6.1 Terra (max) is 2.0× cheaper ($2.00 vs $4.00 per 1M blended).
- GPT-6 Sol (max) streams 1.4× faster (127 vs 91 tokens per second).
At a glance
| Spec | GPT-6.1 Terra | GPT-6 Sol |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Released | 26 Oct 2026 | 22 Sept 2026 |
| Context window (tokens) | 1,050,000 | 1,050,000 |
| Compared at | GPT-6.1 Terra (max) | GPT-6 Sol (max) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $1.00 / $5.00 / $0.050 | $2.00 / $10.00 / $0.200 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | GPT-6.1 Terra (max) | GPT-6 Sol (max) | Leader |
|---|---|---|---|
| Reasoning | 86.2 | 71.4 | GPT-6.1 Terra |
| Coding | – | 67.1 | not comparable |
| Agents & tools | – | 59.8 | not comparable |
| Maths | – | 69.2 | not comparable |
| Knowledge | 74.5 | 69.5 | GPT-6.1 Terra |
| Human preference | – | 64.6 | not comparable |
| Multimodal | 67.5 | 61.3 | GPT-6.1 Terra |
| Long context | 66.3 | 66.8 | level |
| Composite | 82.8 | 82.2 | level |
Where sources disagree
Across the 13 benchmarks both have, GPT-6.1 Terra leads 6, GPT-6 Sol leads 7. Every overall index that rates both puts GPT-6.1 Terra ahead.
| Overall index | GPT-6.1 Terra (max) | GPT-6 Sol (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 65.9 | 66.3 | neck and neck |
| AA Intelligence Index v4.3.2 | 48.1 | 47.6 | GPT-6.1 Terra |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.
| Measure | GPT-6.1 Terra (max) | GPT-6 Sol (max) |
|---|---|---|
| Blended price per 1M tokens | $2.00 | $4.00 |
| Input / output per 1M | $1.00 / $5.00 | $2.00 / $10.00 |
| Cached input per 1M | $0.050 | $0.200 |
| Price per task: chat reply | $0.0019 | $0.0038 |
| Price per task: summarize a 30-page report | $0.015 | $0.030 |
| Price per task: code edit | $0.013 | $0.027 |
| Price per task: agentic coding session | $0.080 | $0.160 |
| Price per task: structured extraction | $0.0030 | $0.0060 |
| Cost to run a full benchmark suite | $0.403 | $1.04 |
| Output speed | 91 tok/s | 127 tok/s |
| Time to first answer | 131.8 s | 132.5 s |
| Time to a complete answer | 137.3 s | 136.4 s |
Per token is not per task: on Artificial Analysis' full suite GPT-6.1 Terra (max) cost $0.403 and GPT-6 Sol (max) $1.04, because GPT-6 Sol (max) used about 1.3× as many tokens for the same work.
Each model is compared at its best-ranked reasoning-effort setting. GPT-6.1 Terra (max) scores 65.9 and takes 132 s to its first answer token; GPT-6.1 Terra (xhigh) scores 65.0 in 18 s, GPT-6.1 Terra (high) scores 64.7 in 7 s. GPT-6 Sol (max) scores 66.3 and takes 133 s to its first answer token; GPT-6 Sol (xhigh) scores 64.1 in 41 s, GPT-6 Sol (high) scores 63.5 in 18 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
99 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | GPT-6.1 Terra (max) | GPT-6 Sol (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 65.9 | 66.3 |
| Composite score | BenchLeader | 82.8 | 82.2 |
| Knowledge score | BenchLeader | 74.5 | 69.5 |
| Long context score | BenchLeader | 66.3 | 66.8 |
| Multimodal score | BenchLeader | 67.5 | 61.3 |
| Reasoning score | BenchLeader | 86.2 | 71.4 |
| Agents & tools score | BenchLeader | – | 59.8 |
| Coding score | BenchLeader | – | 67.1 |
| Human preference score | BenchLeader | – | 64.6 |
| Maths score | BenchLeader | – | 69.2 |
| Blended price $/M | BenchLeader | $2.00 | $4.00 |
| Output speed | BenchLeader | 91 tok/s | 127 tok/s |
| Time to first answer | BenchLeader | 131.8 s | 132.5 s |
| Context window | BenchLeader | 1,050,000 tokens | 1,050,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | – | 94.3% |
| Arena Hard Prompts | Arena (LMArena) | – | 1485 |
| LiveBench 2.0 Reasoning | LiveBench | 88.7%† | – |
| LiveBench 1.0 Reasoning | LiveBench | – | 88.7% |
| Humanity's Last Exam (AA) | Artificial Analysis | 46.3% | 47.9% |
| ARC-AGI-1 | ARC Prize | – | 95.5% |
| ARC-AGI-2 | ARC Prize | – | 89.6% |
| ARC-AGI-3 | ARC Prize | – | 23.0% |
| CritPt | Artificial Analysis | 28.0% | 30.9% |
| MysteryMechanism | Vals AI | – | 30.2% |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 56.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 56.0% |
| LMCA | Epoch AI Benchmarking Hub | – | 59.1% |
| DTBench | Epoch AI Benchmarking Hub | – | 97.3% |
| Coding | |||
| SciCode | SciCode | – | 57.6% |
| FrontierCode | Cognition | – | 49.3% |
| Arena Coding | Arena (LMArena) | – | 1519 |
| Arena WebDev | Arena (LMArena) | – | 1681 |
| LiveBench 2.0 Coding | LiveBench | 90.8%† | – |
| LiveBench 1.0 Coding | LiveBench | – | 81.8% |
| SciCode (AA) | Artificial Analysis | 55.1% | 57.6% |
| IOI | Vals AI | – | 82.6% |
| Code Migration | Vals AI | – | 57.2% |
| ProgramBench | Vals AI | – | 2.0% |
| Vibe Code Bench v1.1 | Vals AI | – | 87.8% |
Show all 99 benchmarks
| Metric | Publisher | GPT-6.1 Terra (max) | GPT-6 Sol (max) |
|---|---|---|---|
| Coding | |||
| ALE-Bench | Epoch AI Benchmarking Hub | – | 2462 |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 55.6% | 43.9% |
| FrontierCode 1.1 (AA) | Artificial Analysis | 36.0% | – |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 49.4% |
| APEX-Agents | Mercor | – | 54.3% |
| Arena Agent | Arena (LMArena) | – | 8.6 |
| LiveBench Long Agentic | LiveBench | 48.6%† | – |
| LiveBench Browser | LiveBench | 93.1%† | – |
| LiveBench Agentic Coding | LiveBench | – | 52.9% |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 83.2% |
| ITBench SRE (AA) | Artificial Analysis | – | 49.4% |
| CyberBench | Vals AI | – | 78.0% |
| Finance Agent v2 | Vals AI | – | 49.0% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 1.7% |
| Legal Research Bench | Vals AI | – | 28.9% |
| SREBench | Vals AI | – | 30.5% |
| Tax Agent Bench | Vals AI | – | 15.0% |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 44.4% |
| Terminal-Bench Science | Vals AI | – | 30.0% |
| Arena Search | Arena (LMArena) | – | 1228 |
| Vending-Bench 2 | Andon Labs | – | 14427.9† |
| AutomationBench | Artificial Analysis | 60.2% | 61.6% |
| GDP.pdf (AA) | Artificial Analysis | 28.6% | 25.2% |
| Harvey LAB-AA v1.1 | Harvey | – | 3.6% |
| AA-Briefcase v1.1 | Artificial Analysis | 1402 | 1477 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 57.6% | 30.0% |
| CWE-Bench (AA) | Artificial Analysis | – | 64.2% |
| DeepSec-Bench (AA) | Artificial Analysis | – | 46.3% |
| CyberGym end-to-end (AA) | Artificial Analysis | – | 0.0% |
| FACTS Search | – | 86.2%† | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 89.8% |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | – | 90.0% |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 100.0% |
| ProofBench | Vals AI | – | 83.0%† |
| LiveBench Mathematics | LiveBench | – | 96.4% |
| Arena Maths | Arena (LMArena) | – | 1450 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 60.7% |
| LiveBench 2.0 Data Analysis | LiveBench | 82.3%† | – |
| LiveBench Research | LiveBench | 73.9%† | – |
| LiveBench 1.0 Data Analysis | LiveBench | – | 81.2% |
| AA-Omniscience | Artificial Analysis | 29.8 | 27.1 |
| PRBench Legal | Scale AI SEAL | – | 38.6%† |
| BioMysteryBench | Vals AI | – | 74.8% |
| Excel Modeling Benchmark | Vals AI | – | 71.5% |
| MedCode | Vals AI | – | 47.1% |
| MedScribe | Vals AI | – | 82.0% |
| Public Benefits Bench v1.1 | Vals AI | – | 56.6% |
| EBR-bench | Epoch AI Benchmarking Hub | – | 53.3% |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 26.4% |
| AA-Omniscience: accuracy | Artificial Analysis | 49.1% | 54.5% |
| AA-Omniscience: non-hallucination | Artificial Analysis | 62.0% | 39.9% |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 85.3% |
| LiveBench Instruction Following | LiveBench | – | 68.6% |
| Arena Instruction Following | Arena (LMArena) | – | 1450 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1459 |
| Arena Creative Writing | Arena (LMArena) | – | 1435 |
| Arena Multi-turn | Arena (LMArena) | – | 1468 |
| Arena Longer Queries | Arena (LMArena) | – | 1468 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1240 |
| LiveBench Design | LiveBench | 82.3%† | – |
| MMMU-Pro | Artificial Analysis | 84.7% | 83.0% |
| SAGE | Vals AI | – | 44.8% |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | – | 36.9%† |
| AA-3D | Artificial Analysis | – | 1121 |
| Long context | |||
| AA-LCR | Artificial Analysis | 82.7% | 83.7% |
| MLCR | Artificial Analysis | – | 33.9% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | – | 163.7† |
| LiveBench 2.0 | LiveBench | 77.2%† | – |
| LiveBench 1.0 | LiveBench | – | 79.3% |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 48.1 | 47.6 |
| Vals RSI Index | Vals AI | – | 28.1% |
| Vals Science Index | Vals AI | – | 45.0% |
| AA Cyber Index | Artificial Analysis | – | 36.8 |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 18.2%† | 13.5%† |
Data as of 2026-10-27. Best configuration of each model; every score links to its source on the model pages.
What changed
- GPT-6 Sol (max): 1 score revision.
- GPT-6 Sol (max): 3 new results (Harvey's Legal Agent Benchmark v1, Vals RSI Index, Vals Science Index).
- GPT-6 Sol (max): 1 score revision.
- GPT-6 Sol (max): 2 score revisions.
- GPT-6 Sol (max): BenchLeader Index 65.6 → 66.6.
- GPT-6 Sol (max): 3 new results (GDPval-AA v2.1, AA-Omniscience: accuracy, AA-Omniscience: non-hallucination).
- GPT-6 Sol (max): 1 score revision.
- GPT-6 Sol (max): 1 new result (SREBench); 2 score revisions.
- GPT-6 Sol (max): 2 new results (Chess Puzzles, Arena Search); 3 score revisions.
- GPT-6 Sol (max): 1 score revision.
Related comparisons
- GPT-6.1 Terra vs Claude Opus 5.5
- GPT-6.1 Terra vs Claude Fable 5.1
- GPT-6.1 Terra vs GPT-6 Astra
- GPT-6 Sol vs Claude Opus 5.5
- GPT-6 Sol vs Claude Fable 5.1
- GPT-6 Sol vs GPT-6 Astra
- GPT-6 Sol vs Muse Wonder Full
- GPT-6.1 Sol vs GPT-6 Sol
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
GPT-6.1 Terra vs GPT-6 Sol: questions
- Is GPT-6.1 Terra better than GPT-6 Sol?
- GPT-6.1 Terra (max) and GPT-6 Sol (max) are neck and neck on quality (65.9 vs 66.3, within the ±8.0 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 2026-10-27, so check the category scores for your use.
- Which is cheaper, GPT-6.1 Terra or GPT-6 Sol, and will that change?
- GPT-6.1 Terra is cheaper today: $2.00 against $4.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Which is better for long documents?
- They are level on long-context benchmarks (66 vs 67). Both accept 1,050,000 tokens of context.
- Which has lower latency?
- GPT-6.1 Terra (max) answers first: 131.8 s against 132.5 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Which is faster, GPT-6.1 Terra or GPT-6 Sol?
- GPT-6 Sol streams faster: 127 against 91 output tokens per second.
- Do independent benchmarks agree on GPT-6.1 Terra vs GPT-6 Sol?
- Across the 13 benchmarks both have, GPT-6.1 Terra leads 6, GPT-6 Sol leads 7. Every overall index that rates both puts GPT-6.1 Terra ahead.
- When was GPT-6.1 Terra released?
- GPT-6.1 Terra was released on 26 Oct 2026.