Compare / GPT-6.1 Sol vs GPT-6 Sol
GPT-6.1 Sol vs GPT-6 Sol
Which is cheaper, which is more capable, and which does better at each kind of work, from 74 results on 8 sources that measured both models.
Of the 74 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee).
GPT-6.1 Sol or GPT-6 Sol? The short answer
GPT-6.1 Sol is the newer version at about the same price, and it scores higher (Spring Prompt overall 80 against 68): upgrade.
- Spring Prompt overall: GPT-6.1 Sol 80, GPT-6 Sol 68 (out of 100; how the score works).
- They cost about the same to run: $0.008 and $0.009 per product listing on CatalogBench.
- GPT-6.1 Sol scores higher on the Artificial Analysis Intelligence Index: 51.8 against 47.6.
- GPT-6.1 Sol is newer: released 29 Sep 2026, against 22 Sep 2026 for GPT-6 Sol.
- On our own benchmarks, on the results both models have: GPT-6.1 Sol does better for product listings and speed under pressure.
- On third-party benchmarks, on the results both models have: GPT-6.1 Sol does better for agents and tool use, professional work, reasoning and knowledge, writing and sticking to the facts.
Head to head
Every fact side by side
| GPT-6.1 Sol | GPT-6 Sol | |
|---|---|---|
| Price per million tokens | $2.00 in · $10.00 out | $2.00 in · $10.00 out |
| Blended (3 in : 1 out) | $4.00 | $4.00 |
| Cheapest host, blended | $4.00 (Amazon Bedrock) | $4.00 (Amazon Bedrock) |
| Cost per product listing (CatalogBench) | $0.008 | $0.009 |
| Cached input, per million | $0.10 cached input | $0.20 cached input |
| Intelligence Index | 51.8 | 47.6 |
| Spring Prompt overall | 80 | 68 |
| Output speed, tokens a second | 53 | – |
| Context window | 1,050,000 tokens | 1,050,000 tokens |
| Released | 29 Sep 2026 (newer) | 22 Sep 2026 |
| Weights | Closed | Closed |
| Developer based in | the US | the US |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.
Their slides, side by side
The same brief for both: Manchester store investment review for Hearthside Coffee, an invented company. First slide of each deck from DeckBench.
From our research
Every shared result
Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.
| Measure | GPT-6.1 Sol | GPT-6 Sol |
|---|---|---|
| BulletBench measured by Spring Prompt · 3 results | ||
| Cost per game · Bullet 60sUS dollars, lower is better 50 · 52 of 59 measured | $0.0210 | $0.0297no reasoning |
| Ladder Elo · Bullet 60sladder Elo, higher is better 2 · 38 of 59 measured | 928Ultrafast (low reasoning) | 445no reasoning |
| Games lost on time · Bullet 60s% of games, lower is better 31 · 39 of 59 measured | 25.0%Ultrafast (low reasoning) | 50.0%no reasoning |
| CatalogBench measured by Spring Prompt · 3 results | ||
| Cost per productUS dollars, lower is better 16 · 17 of 33 measured | $0.0084 | $0.0085 |
| Reliably publish-ready% of products, higher is better 1 · 4 of 32 measured | 75.0% | 66.1% |
| Reliably publish-ready · sales brief% of products, higher is better 2 · 2 of 32 measured | 67.9% | 67.9% |
| DeckBench measured by Spring Prompt · 3 results | ||
| Cost per deckUS dollars, lower is better 21 · 25 of 33 measured | $0.15 | $0.21 |
| Deck ratingrating, higher is betterThe rating weighs each win by how strong the other deck was; the win rate counts wins against whichever decks a model happened to meet, so the two can disagree. 5 · 3 of 33 measured | 1,391 | 1,456 |
| Accurate decks% of tasks, higher is better 1 · 5 of 33 measured | 100.0% | 83.3% |
| APEX-Agents reported by APEX-Agents · 1 result | ||
| Tasks passed% of tasks, higher is better 10 · 17 of 37 measured | 60.0%max reasoning | 54.3%max reasoning |
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 18 · 55 of 387 measured | 1,483max reasoning | 1,457max reasoning |
| Overall · Text factualityArena rating, higher is better 37 · 90 of 163 measured | 1,463max reasoning | 1,434max reasoning |
| Business, management and finance · TextArena rating, higher is better 27 · 74 of 380 measured | 1,475max reasoning | 1,446max reasoning |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 7 · 11 of 249 measured | 51.8max reasoning | 47.6max reasoning |
| Humanity's Last Exam% of questions, higher is better 8 · 16 of 250 measured | 52.9%max reasoning | 47.9%max reasoning |
| Terminal-Bench 4.0% of tasks, higher is better 6 · 11 of 120 measured | 56.1%max reasoning | 43.9%max reasoning |
| SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result | ||
| Correct answers% of questions, higher is better 2 · 14 of 76 measured | 73.9%max reasoning | 60.7%max reasoning |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 17 · 57 of 230 measured | 67.7high reasoning | 55.6high reasoning |
| Requested-length error · UGI% off the requested word count, lower is better 1 · 13 of 230 measured | 0.0%high reasoning | 4.0%high reasoning |
| Style adherence · UGIscore from 0 to 1, higher is better 39 · 19 of 230 measured | 0.37high reasoning | 0.39xhigh reasoning |
Show all 74 results (54 more)
| Measure | GPT-6.1 Sol | GPT-6 Sol |
|---|---|---|
| BulletBench measured by Spring Prompt · 2 results | ||
| Invalid moves · Bullet 60s% of moves, lower is better 1 · 1 of 59 measured | 0.0% | 0.0%no reasoning |
| Median move time · Bullet 60smilliseconds, lower is better 37 · 40 of 59 measured | 1.4 sUltrafast (low reasoning) | 1.6 sno reasoning |
| CatalogBench measured by Spring Prompt · 28 results | ||
| Channel compliance% of products, higher is better 1 · 1 of 33 measured | 100.0% | 100.0% |
| Channel rules broken% of products, lower is better 1 · 1 of 33 measured | 0.0% | 0.0% |
| Channel rules broken · sales brief% of products, lower is better 1 · 17 of 33 measured | 0.0% | 0.6% |
| Claims to check% of products, lower is better 1 · 1 of 31 measured | 0.0% | 0.0% |
| Claims to check · sales brief% of products, lower is better 1 · 1 of 31 measured | 0.0% | 0.0% |
| Conflicts caught% of conflicts, higher is better 1 · 1 of 33 measured | 100.0% | 100.0% |
| Content quality% of checks, higher is better 3 · 8 of 33 measured | 98.6% | 97.8% |
| Content quality · sales brief% of checks, higher is better 2 · 8 of 33 measured | 98.8% | 98.3% |
| Decision accuracy% of decisions, higher is better 3 · 7 of 33 measured | 98.7% | 98.0% |
| Failed outputs% of products, lower is better 1 · 1 of 33 measured | 0.0% | 0.0% |
| Failed outputs · sales brief% of products, lower is better 1 · 1 of 33 measured | 0.0% | 0.0% |
| Field accuracy% of missing fields, higher is better 8 · 15 of 33 measured | 94.4% | 93.7% |
| Invented values% of filled values, lower is better 25 · 12 of 33 measured | 2.2% | 1.0% |
| Missing UK information% of products, lower is better 1 · 1 of 33 measured | 0.0% | 0.0% |
| Missing UK information · sales brief% of products, lower is better 1 · 1 of 33 measured | 0.0% | 0.0% |
| Not findable% of products, lower is better 19 · 25 of 33 measured | 4.8% | 7.7% |
| Not findable · sales brief% of products, lower is better 22 · 27 of 33 measured | 5.4% | 7.1% |
| Publish-ready listings% of products, higher is better 3 · 5 of 33 measured | 78.0% | 75.0% |
| Publish-ready listings · sales brief% of products, higher is better 5 · 1 of 33 measured | 72.0% | 76.2% |
| Time per productseconds, lower is better 11 · 13 of 33 measured | 10.2 | 10.7 |
| Unsupported claimsclaims per product, lower is better 1 · 5 of 33 measured | 0.00 | 0.08 |
| Unsupported claims% of products, lower is better 1 · 5 of 33 measured | 0.0% | 1.8% |
| Unsupported claims · sales briefclaims per product, lower is better 2 · 3 of 33 measured | 0.07 | 0.09 |
| Unsupported claims · sales brief% of products, lower is better 5 · 4 of 33 measured | 3.6% | 3.0% |
| Wrong attributes% of products, lower is better 16 · 8 of 33 measured | 16.7% | 14.3% |
| Wrong attributes · sales brief% of products, lower is better 20 · 4 of 33 measured | 19.1% | 13.7% |
| Wrong category or variant% of products, lower is better 6 · 27 of 33 measured | 1.8% | 3.6% |
| Wrong category or variant · sales brief% of products, lower is better 6 · 23 of 33 measured | 1.8% | 3.0% |
| DeckBench measured by Spring Prompt · 14 results | ||
| Caveat dropped% of tasks, lower is better 1 · 1 of 33 measured | 0.0% | 0.0% |
| Clean layout% of tasks, higher is better 3 · 8 of 33 measured | 83.3% | 66.7% |
| Design quality% of the maximum, higher is better 12 · 2 of 33 measured | 71.4% | 87.9% |
| Draft figure quoted% of tasks, lower is better 1 · 1 of 33 measured | 0.0% | 0.0% |
| Findings missing% of tasks, lower is better 1 · 23 of 33 measured | 0.0% | 16.7% |
| Head-to-head win rate% of comparisons, higher is betterThe rating weighs each win by how strong the other deck was; the win rate counts wins against whichever decks a model happened to meet, so the two can disagree. 5 · 2 of 33 measured | 81.0% | 87.5% |
| Layout defects% of tasks, lower is better 3 · 8 of 33 measured | 16.7% | 33.3% |
| Misleading metric used% of tasks, lower is better 1 · 1 of 33 measured | 0.0% | 0.0% |
| Presentable decks% of tasks, higher is better 3 · 3 of 33 measured | 50.0% | 50.0% |
| Recommendation late or wrong% of tasks, lower is better 1 · 1 of 33 measured | 0.0% | 0.0% |
| Slides needing work% of tasks, lower is better 17 · 1 of 33 measured | 50.0% | 0.0% |
| Time per deckseconds, lower is better 22 · 20 of 33 measured | 179 | 169 |
| Unsupported claims% of tasks, lower is better 1 · 1 of 33 measured | 0.0% | 0.0% |
| Unsupported numbers% of tasks, lower is better 1 · 1 of 33 measured | 0.0% | 0.0% |
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 8 results | ||
| Confirmed task success · AgentIPS effect estimate, higher is better 2 · 10 of 48 measured | 0.15max reasoning, arena agent | 0.07max reasoning, arena agent |
| Creative writing · TextArena rating, higher is better 21 · 47 of 385 measured | 1,460max reasoning | 1,442max reasoning |
| Expert prompts · TextArena rating, higher is better 4 · 41 of 338 measured | 1,543max reasoning | 1,498max reasoning |
| Instruction following · TextArena rating, higher is better 10 · 50 of 387 measured | 1,490max reasoning | 1,453max reasoning |
| Praise over complaint · AgentIPS effect estimate, higher is better 6 · 7 of 48 measured | 0.26max reasoning, arena agent | 0.23max reasoning, arena agent |
| Steerability · AgentIPS effect estimate, higher is better 3 · 2 of 48 measured | 0.11max reasoning, arena agent | 0.11max reasoning, arena agent |
| Tool grounding · AgentIPS effect estimate, higher is better 1 · 30 of 48 measured | 0.00max reasoning, arena agent | 0.00max reasoning, arena agent |
| Writing, literature and language · TextArena rating, higher is better 17 · 59 of 386 measured | 1,472max reasoning | 1,439max reasoning |
| Artificial Analysis reported by Artificial Analysis · 2 results | ||
| Long-context reasoning (AA-LCR)% of questions, higher is better 7 · 11 of 241 measured | 84.0%low reasoning | 83.7%high reasoning |
| SciCode% of problems, higher is better 26 · 18 of 121 measured | 55.8%high reasoning | 57.6%max reasoning |
Compare them with other models
Quick answers
Is GPT-6.1 Sol better than GPT-6 Sol?
GPT-6.1 Sol is the newer version at about the same price, and it scores higher (Spring Prompt overall 80 against 68): upgrade.
Which is cheaper, GPT-6.1 Sol or GPT-6 Sol?
They cost about the same to run: $0.008 and $0.009 per product listing on CatalogBench.
Which is better for product listings, GPT-6.1 Sol or GPT-6 Sol?
GPT-6.1 Sol ranks 2 of 32 models on sale for turning a sparse product feed and photos into listings that can go live, against 3 for GPT-6 Sol.
Which is better for decks from an analysis, GPT-6.1 Sol or GPT-6 Sol?
GPT-6 Sol ranks 3 of 32 models on sale for turning a finished analysis into a deck you could present as it is, against 5 for GPT-6.1 Sol.
Which is better for agents and tool use, GPT-6.1 Sol or GPT-6 Sol?
GPT-6.1 Sol ranks 6 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 8 for GPT-6 Sol.
Which is better for professional work, GPT-6.1 Sol or GPT-6 Sol?
GPT-6.1 Sol ranks 9 of 51 models on sale for real tasks from banking, consulting and law, business documents and freelance projects, against 13 for GPT-6 Sol.
Which is better for reasoning and knowledge, GPT-6.1 Sol or GPT-6 Sol?
GPT-6.1 Sol ranks 6 of 187 models on sale for hard questions across science, maths and general knowledge, against 14 for GPT-6 Sol.
Run GPT-6.1 Sol and GPT-6 Sol on your own prompt.
Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.

