GPT-6.1 Terra vs GPT-6.2 Sol
Full profiles: GPT-6.1 Terra (OpenAI) and GPT-6.2 Sol (OpenAI): every benchmark, price and rank.
Updated · Data from 11 sources
As of 19 Nov 2026, GPT-6.1 Terra and GPT-6.2 Sol are neck and neck on quality (63.2 vs 64.6 on the BenchLeader Index, inside the ±3.6 margin), and GPT-6.1 Terra is 2.0× cheaper at $2.00 vs $4.00 per 1M tokens blended. GPT-6.2 Sol leads in every category we measure both in.
Key facts (as of 19 Nov 2026)
- GPT-6.1 Terra scores 63.2 on the BenchLeader Index and GPT-6.2 Sol scores 64.6 (BenchLeader, 19 Nov 2026).
- GPT-6.1 Terra costs $2.00 per 1M tokens blended (list price, 19 Nov 2026).
- GPT-6.2 Sol costs $4.00 per 1M tokens blended (list price, 19 Nov 2026).
- Of the 34 benchmarks both models have, GPT-6.2 Sol leads 29 (BenchLeader, 19 Nov 2026).
- On Arena WebDev, GPT-6.1 Terra is rated 1683 and GPT-6.2 Sol 1757 (LMArena, as published by 19 Nov 2026).
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 |
|---|---|---|---|
| Coding | GPT-6.2 Sol | 75 vs 68 category score; Arena WebDev 1757 vs 1683 | Medium |
| Agents & tool use | GPT-6.2 Sol | 65 vs 62 category score; Terminal-Bench 61.5% vs 53.3% | Medium |
| Reasoning | GPT-6.2 Sol | 70 vs 67 category score; HLE-Diamond (AA) 64.0% vs 47.3% | Medium |
| Knowledge | GPT-6.2 Sol | 65 vs 61 category score; AA-Omniscience v1.1 40.4 vs 29.6 | Medium |
| 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 | GPT-6.2 Sol | 78.8 s (GPT-6.2 Sol (max)) vs 159.4 s (GPT-6.1 Terra (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-6.2 Sol (max) are neck and neck on quality (63.2 vs 64.6, within the ±3.6 margin).
- GPT-6.2 Sol (max) is stronger in agents & tools, coding, composite, knowledge, reasoning.
- GPT-6.1 Terra (max) is 2.0× cheaper ($2.00 vs $4.00 per 1M blended).
At a glance
| Spec | GPT-6.1 Terra | GPT-6.2 Sol |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Released | 26 Oct 2026 | 17 Nov 2026 |
| Context window (tokens) | 1,050,000 | 1,050,000 |
| Compared at | GPT-6.1 Terra (max) | GPT-6.2 Sol (max) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $1.00 / $5.00 / $0.050 | $2.00 / $10.00 / $0.100 |
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-6.2 Sol (max) | Leader |
|---|---|---|---|
| Reasoning | 67.2 | 70.1 | GPT-6.2 Sol |
| Coding | 68.0 | 74.5 | GPT-6.2 Sol |
| Agents & tools | 62.1 | 65.1 | GPT-6.2 Sol |
| Maths | 71.2 | – | not comparable |
| Knowledge | 60.6 | 65.4 | GPT-6.2 Sol |
| Multimodal | 66.8 | – | not comparable |
| Long context | 66.0 | – | not comparable |
| Composite | 62.6 | 64.5 | GPT-6.2 Sol |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Maths, Instruction following, Long context, Multimodal, Human preference.
Where sources disagree
Across the 34 benchmarks both have, GPT-6.1 Terra leads 5, GPT-6.2 Sol leads 29. Every overall index that rates both puts GPT-6.2 Sol ahead.
| Overall index | GPT-6.1 Terra (max) | GPT-6.2 Sol (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 63.2 | 64.6 | neck and neck |
| AA Intelligence Index v5.0.1 | 51.3 | 57.3 | GPT-6.2 Sol |
| Vals Index | 60.5 | 66.1 | GPT-6.2 Sol |
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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | GPT-6.1 Terra (max) | GPT-6.2 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 | $0.100 |
| 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 |
| Agentic coding session, input mostly cached | $0.037 | $0.074 |
| Cost per benchmark task (AA Index) | $0.961 | $1.01 |
| Output tokens per task (AA Index) | 60k | 40k |
| Of which reasoning | 39k | 23k |
| Time per task (AA Index) | 15 min | 9 min |
| Output speed | 65 tok/s | 74 tok/s |
| Time to first answer | 159.4 s | 78.8 s |
| Time to a complete answer, last measured 13 Nov 2026 | 375.7 s | – |
Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $0.961 on GPT-6.1 Terra (max) and $1.01 on GPT-6.2 Sol (max), and GPT-6.1 Terra (max) wrote 1.5× as many output tokens for the same work, which a per-token price hides.
Each model is compared at its best-ranked reasoning-effort setting. GPT-6.1 Terra (max) scores 63.2 and takes 159 s to its first answer token; GPT-6.1 Terra (xhigh) scores 59.4 in 32 s, GPT-6.1 Terra (high) scores 59.0 in 12 s. GPT-6.2 Sol (max) scores 64.6 and takes 79 s to its first answer token; GPT-6.2 Sol (xhigh) scores 63.3 in 32 s, GPT-6.2 Sol (high) scores 62.3 in 12 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
102 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-6.2 Sol (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 63.2 | 64.6 |
| Agents & tools score | BenchLeader | 62.1 | 65.1 |
| Coding score | BenchLeader | 68.0 | 74.5 |
| Composite score | BenchLeader | 62.6 | 64.5 |
| Knowledge score | BenchLeader | 60.6 | 65.4 |
| Long context score | BenchLeader | 66.0 | – |
| Maths score | BenchLeader | 71.2 | – |
| Multimodal score | BenchLeader | 66.8 | – |
| Reasoning score | BenchLeader | 67.2 | 70.1 |
| Blended price $/M | BenchLeader | $2.00 | $4.00 |
| Output speed | BenchLeader | 65 tok/s | 74 tok/s |
| Time to first answer | BenchLeader | 159.4 s | 78.8 s |
| Context window | BenchLeader | 1,050,000 tokens | 1,050,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 94.3% | – |
| SimpleBench | SimpleBench | 72.2%† | – |
| LiveBench 2.0 Reasoning | LiveBench | 88.7% | 90.6% |
| Humanity's Last Exam (AA) | Artificial Analysis | 46.3% | – |
| HLE-Diamond (AA) | Artificial Analysis | 47.3% | 64.0% |
| Kagi LLM Benchmark | Kagi LLM Benchmark | – | 67.0%† |
| ARC-AGI-1 | ARC Prize | – | 97.5% |
| ARC-AGI-2 | ARC Prize | – | 85.8% |
| ARC-AGI-3 | ARC Prize | – | 98.2% |
| CritPt | Artificial Analysis | 28.0% | – |
| CritPt v2 hard subset (AA) | Artificial Analysis | 68.0% | 62.5% |
| MysteryMechanism | Vals AI | – | 36.9% |
| HLE-Diamond (Scale) | Scale AI SEAL | 35.7%† | 56.5%† |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 74.0% | – |
| Coding | |||
| SciCode | SciCode | 55.1% | – |
| Arena WebDev | Arena (LMArena) | 1683 | 1757 |
| LiveBench 2.0 Coding | LiveBench | 89.2% | 83.7% |
| Vibe Code Bench v1.1 | Vals AI | 84.0% | 87.6% |
| Vibe Code Bench 1-100 v1.1 | Vals AI | – | 40.9% |
| SWE Atlas v1.1 | Scale AI SEAL | 57.7%† | 60.5%† |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | 54.0%† | 61.3%† |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | 63.3%† | 64.4%† |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | 55.7%† | 55.7%† |
| MirrorCode | Epoch AI Benchmarking Hub | 76.7% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 2608.8 | – |
Show all 102 benchmarks
| Metric | Publisher | GPT-6.1 Terra (max) | GPT-6.2 Sol (max) |
|---|---|---|---|
| Coding | |||
| WeirdML v3 | WeirdML | 28.1%† | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 55.6% | 60.1% |
| GameBench 2 Overall | DuelLab GameBench 2 | 81.1† | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 85.9† | – |
| Design Arena Website | Design Arena | 1286† | – |
| FrontierCode 1.1 (AA) | Artificial Analysis | 36.0% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 42.3% | 44.4% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 53.3% | 61.5% |
| APEX-Agents | Mercor | 68.3% | – |
| Arena Agent | Arena (LMArena) | 10.5 | 11.3 |
| LiveBench Long Agentic | LiveBench | 55.3% | 63.6% |
| LiveBench Browser | LiveBench | 93.1% | 88.2% |
| HiL-Bench | Scale AI SEAL | 68.0%† | – |
| GDPval-AA v2.1 | Artificial Analysis | 1476 | – |
| Analyst Agent (AA) | Artificial Analysis | – | 53.8% |
| Finance Agent v2.1 | Vals AI | 56.0% | 58.9% |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 1.7% | 12.1% |
| Legal Research Bench | Vals AI | 26.0% | 37.0% |
| Tax Agent Bench | Vals AI | 17.1% | 24.8% |
| Terminal-Bench 4.0 (Vals) | Vals AI | 49.5% | 60.6% |
| Terminal-Bench Science | Vals AI | – | 58.6% |
| Arena Agent Task Completion | Arena (LMArena) | 8.5 | 10.9 |
| Vending-Bench 2 | Andon Labs | 9107.5† | – |
| SpireClimb | Epoch AI Benchmarking Hub | 22.3% | – |
| AutomationBench | Artificial Analysis | 60.2% | 71.3% |
| GDP.pdf (AA) | Artificial Analysis | 28.6% | 30.0% |
| Harvey LAB-AA v1.1 | Harvey | – | 11.1% |
| EnterpriseOps-Gym | Artificial Analysis | – | 28.9% |
| AA-Briefcase v1.1 | Artificial Analysis | 1399 | 1612 |
| GDPx | GDPx by SemiAnalysis | 8.5% | – |
| Design Arena Agentic | Design Arena | 1176† | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 57.6% | 67.6% |
| CWE-Bench (AA) | Artificial Analysis | – | 61.7% |
| DeepSec-Bench (AA) | Artificial Analysis | – | 51.6% |
| CyberGym end-to-end (AA) | Artificial Analysis | – | 0.0% |
| MKA (AA) | Artificial Analysis | 43.8% | – |
| FACTS Search | 92.7%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 90.9% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 92.7% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 100.0% | – |
| Autoform-Hard | Vals AI | – | 85.7% |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 57.3% | – |
| LiveBench 2.0 Data Analysis | LiveBench | 82.3% | 81.1% |
| LiveBench Research | LiveBench | 79.1% | 90.1% |
| AA-Omniscience v1.1 | Artificial Analysis | 29.6 | 40.4 |
| PRBench Legal | Scale AI SEAL | – | 43.3%† |
| BioMysteryBench | Vals AI | – | 77.8% |
| Excel Modeling Benchmark v1.1 | Vals AI | 73.3% | 74.3% |
| DrugDiscoveryBench | Scale AI SEAL | 58.1%† | 62.2%† |
| EBR-bench | Epoch AI Benchmarking Hub | 78.1% | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 47.6% | 61.6% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 65.5% | 44.6% |
| FACTS Parametric | 70.8%† | – | |
| Instruction following | |||
| MultiChallenge | Scale AI SEAL | 74.2%† | 72.0%† |
| Multimodal | |||
| LiveBench Design | LiveBench | 79.7% | 80.0% |
| MMMU-Pro | Artificial Analysis | 84.7% | – |
| Humanity's Sixth Sense | Scale AI SEAL | – | 56.8%† |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 42.1%† | – |
| Furniture Assembly | Epoch AI Benchmarking Hub | 79.2% | – |
| VIALS-AA | Handshake AI | 60.3% | 62.7% |
| AA-3D | Artificial Analysis | – | 1259 |
| FACTS Multimodal | 48.8%† | – | |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 82.7% | – |
| MLCR | Artificial Analysis | 30.6% | 37.2% |
| FACTS Grounding | 84.2%† | – | |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 167.7† | – |
| LiveBench 2.0 | LiveBench | 78.6% | 80.3% |
| AA Intelligence Index v5.0.1 | Artificial Analysis | 51.3 | 57.3 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 48.1 | – |
| AA Progress Index v1 | Artificial Analysis | 345.2 | – |
| Vals Index | Vals AI | 60.5 | 66.1 |
| Vals Finance Index | Vals AI | 53.3% | 56.7% |
| Vals Science Index | Vals AI | – | 57.8% |
| Vals Legal Index | Vals AI | 58.8% | 66.7% |
| AA Cyber Index | Artificial Analysis | – | 37.8 |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 18.2%† | – |
| DistressBench | Scale AI SEAL | 65.9%† | – |
Data as of 2026-11-19. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261114-ca113f475f5e (https://benchmarks.duellab.org/releases/gb2-20261114-ca113f475f5e/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- GPT-6.2 Sol (max): BenchLeader Index 63.2 → 64.6.
- GPT-6.1 Terra (max): 3 score revisions.
- GPT-6.2 Sol (max): 4 new results (VIALS-AA, Arena WebDev, Arena Agent…).
- GPT-6.2 Sol (max): BenchLeader Index 62.4 → 63.2.
- GPT-6.2 Sol (max): 2 new results (Vibe Code Bench 1-100 v1.1, Terminal-Bench).
- GPT-6.1 Terra (max): BenchLeader Index 64.1 → 63.5.
- GPT-6.1 Terra (max): 2 score revisions.
- GPT-6.1 Terra (max): 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
- GPT-6.1 Terra (max): BenchLeader Index 64.7 → 64.1.
- GPT-6.1 Terra (max): 1 new result (Terminal-Bench).
Related comparisons
- GPT-6.1 Terra vs Claude Fable 5.2
- GPT-6.1 Terra vs GPT-6.2 Astra
- GPT-6.1 Terra vs Gemini 4 Carbon
- GPT-6.2 Sol vs Claude Fable 5.2
- GPT-6.2 Sol vs GPT-6.2 Astra
- GPT-6.2 Sol vs Gemini 4 Carbon
- GPT-6.2 Sol vs Claude Opus 5.5
- GPT-6.1 Sol vs GPT-6.2 Sol
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
GPT-6.1 Terra vs GPT-6.2 Sol: questions
- Is GPT-6.1 Terra better than GPT-6.2 Sol?
- GPT-6.1 Terra (max) and GPT-6.2 Sol (max) are neck and neck on quality (63.2 vs 64.6, within the ±3.6 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 19 Nov 2026, so check the category scores for your use.
- GPT-6.1 Terra vs GPT-6.2 Sol: which is cheaper, 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.
- Is GPT-6.1 Terra or GPT-6.2 Sol better for coding?
- GPT-6.2 Sol scores higher in coding (75 vs 68 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1683 for GPT-6.1 Terra against 1757 for GPT-6.2 Sol.
- Which is faster, GPT-6.1 Terra or GPT-6.2 Sol?
- GPT-6.2 Sol streams faster (74 vs 65 output tokens per second, Artificial Analysis 7-day median).
- Is GPT-6.1 Terra or GPT-6.2 Sol better for agents and tool use?
- GPT-6.2 Sol scores higher in agentic tasks (65 vs 62 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 53.3% for GPT-6.1 Terra against 61.5% for GPT-6.2 Sol.
More questions (4)
- Which is better for long documents?
- Both accept 1,050,000 tokens of context.
- Which has lower latency?
- GPT-6.2 Sol answers first: 78.8 s against 159.4 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.
- Do independent benchmarks agree on GPT-6.1 Terra vs GPT-6.2 Sol?
- Across the 34 benchmarks both have, GPT-6.1 Terra leads 5, GPT-6.2 Sol leads 29. Every overall index that rates both puts GPT-6.2 Sol ahead.
- When was GPT-6.2 Sol released?
- GPT-6.2 Sol was released on 17 Nov 2026.