Models / GPT-6 Sol
GPT-6 Sol
GPT-6 Sol is best for agents and tool use, and decks from an analysis; pick it when quality matters more than cost. The cheapest model of similar intelligence is DeepSeek-V4.1-Flash-1017, at $0.52 per million tokens against $4.00.
Superseded. GPT-6.1 Sol is OpenAI's newer model in this line, at $4.00 blended: see GPT-6.1 Sol or compare the two.
Results 16 Nov 2026 · 121 results · 12 sources
Test GPT-6 Sol on your prompt → It runs beside the models you could use instead, with every answer checked and costed.
- Price per million tokens
- $2.00 in · $10.00 out
OpenAI's list price, 10 Nov 2026 · compare prices$0.20 cached input · 50% off in batch - Speed
- Not measured
- Intelligence Index
- 47.6
Artificial Analysis, at max reasoning; 28.5–47.6 across 6 settings - Spring Prompt overall
- 8th of 36 score 68 of 100 · how it works
- Spring Prompt Score
- 85 of 100 3rd of 32 · 4 of 5 benchmarks · our own tests only
- Developer
- OpenAI, based in the US
Weights not published - Released
- 22 Sep 2026
1,050,000 tokens of context
Where it stands among the models you could choose
Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.
| Among | Intelligence Index | Spring Prompt overall | Price, blended | Speed |
|---|---|---|---|---|
| Models available today | 11th of 185Claude Opus 5.5 | 8th of 35Claude Fable 5.2 | $4.00 blended, 83rd percentilecheapest: Mistral Nemo | – |
| Models priced $3–10 per million tokens | 6th of 38Claude Opus 5.5 | 5th of 15Claude Opus 5.5 | sets this group | – |
| Models with similar intelligence | sets this group | 1st of 7leads | $4.00 blended, 64th percentilecheapest: DeepSeek-V4.1-Flash-1017 | – |
| Models from developers based in the US | 11th of 92Claude Opus 5.5 | 8th of 21Claude Fable 5.2 | $4.00 blended, 68th percentilecheapest: Gemma 3 4B | – |
The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.
Measured cost per task
API cost recorded in our benchmark runs, excluding judging.
| Task | Benchmark | Cost per task |
|---|---|---|
| Product listing | CatalogBench | ≈ $0.009 |
| Deck | DeckBench | ≈ $0.210 |
| Game of bullet chess | BulletBench | ≈ $0.030 |
Cheapest model that passes
On our benchmarks that define a pass for each task: what one passing answer cost in our run, failed attempts included, and whether a cheaper model passed.
- CatalogBench · cost per 1,000 accepted listings
GPT-6 Sol: $11.36 (126 of 168 attempts), 8 of 25. Cheapest: GPT-6 Luna at $0.70 (114 of 168 attempts). Cheaper and passed at least as often: GPT-6.1 Sol at $10.75 (131 of 168 attempts). - DeckBench · cost per presentable deck
GPT-6 Sol: $0.42 (3 of 6 tasks), 4 of 12. Cheapest: GPT-6.1 Terra at $0.13 (3 of 6 tasks). It passed at least as often.
Cost per attempt divided by the share that passed, at the run date's prices, excluding judging. Each model at its cheapest setting per passing answer. With a handful of tasks, a pass or two either way is within chance. No estimate where a run had missing outputs, because their cost may not have been recorded.
How good is it, and for what?
Each use case ranks the available models its benchmarks measured, then those priced $3–10 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.
Product listingsTurning a sparse product feed and photos into listings that can go live
| Benchmark | GPT-6 Sol | Rank among available | Best available |
|---|---|---|---|
| CatalogBenchCatalogBench: reliably publish-ready | 66.1% | 4th of 32 | GPT-6 Astra 75.0% |
| CatalogBenchCatalogBench (sales brief): reliably publish-ready | 67.9% | 2nd of 32 | GPT-6 Astra 69.6% |
Decks from an analysisTurning a finished analysis into a deck you could present as it is
| Benchmark | GPT-6 Sol | Rank among available | Best available |
|---|---|---|---|
| DeckBenchDeckBench: deck rating | 1,456 | 3rd of 32 | Qwen4-Max 1,585 |
User surveysPlanning a user survey and reading its results without being misled
- SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending
| Benchmark | GPT-6 Sol | Rank among available | Best available |
|---|---|---|---|
| ROASBenchROASBench: overall score | 54.1 | 5th of 32 | Claude Fable 5.2 61.3 |
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls
| Benchmark | GPT-6 Sol | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported | 43.9% | 11th of 107 | Kimi K3.1 Pro 67.2% |
| Vending-Bench 2Vending-Bench 2: money after a year · reported | $14,428 | 2nd of 53 | GPT-6 Astra $15,515 |
- tau2-bench: pending. Its latest results are dated 26 May 2026, before this model was released.
- Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
- OpenHands Index: pending. Its latest results are dated 30 Jun 2026, before this model was released.
- Microsoft STATE-Bench: pending. Its latest results are dated 29 May 2026, before this model was released.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects
| Benchmark | GPT-6 Sol | Rank among available | Best available |
|---|---|---|---|
| APEX-AgentsAPEX-Agents: tasks passed · reported | 54.3% | 17th of 37 | Claude Sonnet 5.5 75.5% |
| GDP.pdfGDP.pdf: professional document tasks · reported | 26.4% | 6th of 31 | GPT-5.6 Sol 30.7% |
- Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge
| Benchmark | GPT-6 Sol | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported | 47.6 | 11th of 185 | Claude Opus 5.5 57.6 |
| Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported | 47.9% | 16th of 186 | Claude Opus 5.5 61.4% |
WritingWhat people prefer in blind comparisons, and judged writing quality
| Benchmark | GPT-6 Sol | Rank among available | Best available |
|---|---|---|---|
| Arena (formerly LMArena)Arena Text: overall · reported | 1,457 | 42nd of 153 | Gemini 4 Argon 1,525 |
| UGI LeaderboardUGI: writing score · reported | 55.6 | 43rd of 124 | Gemini 3.8 Flash 78.6 |
Sticking to the factsSummarising without inventing things, and factual answers
| Benchmark | GPT-6 Sol | Rank among available | Best available |
|---|---|---|---|
| Vectara Hallucination LeaderboardVectara: hallucination rate · reported | 6.5% | 20th of 71 | GPT-5.4 nano 3.1% |
| Arena (formerly LMArena)Arena Text factuality: overall · reported | 1,434 | 71st of 109 | Gemini 4 Argon 1,511 |
| SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported | 60.7% | 14th of 68 | GPT-6 Astra 75.6% |
Speed under pressureGood decisions against a real clock (fast chess)
| Benchmark | GPT-6 Sol | Rank among available | Best available |
|---|---|---|---|
| BulletBenchBulletBench Bullet 60s: ladder Elo | 445 | 13th of 33 | Gemini 3.8 Flash 1,068 |
Nearest alternatives
- Cheaper at similar intelligenceDeepSeek-V4.1-Flash-1017$0.52 blended · Intelligence Index 45.1Compare with GPT-6 Sol →
- OpenAI's newer model in this lineGPT-6.1 Sol$4.00 blended · Intelligence Index 51.8Compare with GPT-6 Sol →
- Open weights at similar intelligenceDeepSeek-V4.1-Flash-1017$0.52 blended · Intelligence Index 45.1Compare with GPT-6 Sol →
Against GPT-6 Sol at $4.00 blended, Intelligence Index 47.6. "Similar intelligence" means within 4 points or better.
Where to run it
6 hosts on OpenRouter at the standard service tier, with a median of $4.20 blended per million tokens. Cheapest first.
| Host | Quantisation | Input | Output | Blended |
|---|---|---|---|---|
| Amazon Bedrock | not stated | $2.00 | $10.00 | $4.00 |
| Azure | not stated | $2.00 | $10.00 | $4.00 |
| OpenAI | not stated | $2.00 | $10.00 | $4.00 |
| Amazon Bedrock | not stated | $2.20 | $11.00 | $4.40 |
| Azure | not stated | $2.20 | $11.00 | $4.40 |
| Azure | not stated | $2.20 | $11.00 | $4.40 |
Other service tiers, not counted above: OpenAI fast $4.00 in, $20.00 out; OpenAI flex $1.00 in, $5.00 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.
Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.
Against the alternatives
The models you would most likely weigh it against: the leaders of the groups above.
Scroll sideways to see every alternative.
| GPT-6 Sol | Claude Opus 5.5 most intelligent at $3–10 per million tokens | DeepSeek-V4.1-Flash-1017 cheapest with similar intelligence | Claude Fable 5.2 highest-scoring overall available today | |
|---|---|---|---|---|
| Price per million tokens | $4.00 | $8.00 | $0.52 | $16.00 |
| Tokens a second | – | 96 | 212 | – |
| Intelligence Index | 47.6 | 57.6 | 45.1 | – |
| Spring Prompt overall | 68 | 82 | 38 | 90 |
| Rank among available models, by use case | ||||
| Product listings | 3rd of 32 | 13th | 28th | 5th |
| Decks from an analysis | 3rd of 32 | 7th | 20th | 4th |
| User surveys | – | 4th | 10th | 1st |
| Marketing planning | 5th of 32 | 9th | 20th | 1st |
| Agents and tool use | 8th of 159 | 3rd | 24th | – |
| Professional work | 13th of 51 | 3rd | – | – |
| Reasoning and knowledge | 14th of 187 | 1st | 24th | – |
| Writing | 50th of 169 | 5th | – | – |
| Sticking to the facts | 48th of 139 | 3rd | – | – |
| Speed under pressure | 11th of 35 | – | 26th | 8th |
| Side by side → | Side by side → | Side by side → | ||
Shaded figures are better than GPT-6 Sol's. A dash means no result.
Research and examples
Where it has been measured
Highest-scoring overall of the 7 models with similar intelligence. 6th most intelligent of the 38 models priced $3–10 per million tokens. Among models available today, in the top quarter (by percentile) for 5 of the 9 use cases measured, led by agents and tool use, and decks from an analysis.
Artificial Analysis lists it but has not published a speed for it yet
- BulletBench5 results
- CatalogBench31 results
- DeckBench17 results
- ROASBench9 results
- APEX-Agents1 result
- Arena (formerly LMArena)11 results
- Artificial Analysis30 results
- GDP.pdf1 result
- SimpleQA Verified (Epoch AI)1 result
- UGI Leaderboard12 results
- Vectara Hallucination Leaderboard2 results
- Vending-Bench 21 result
- Berkeley Function Calling Leaderboard (BFCL) V4Pending: latest results 16 Dec 2025
- Microsoft STATE-BenchPending: latest results 1 Jul 2026
- OpenHands IndexPending: latest results 30 Jun 2026
- tau2-benchPending: latest results 3 Aug 2026
- SurveyBenchNot measured
- Remote Labor IndexNot measured
Every result
121 published results from 12 sources, each in the source's own units, with the configuration that produced it.
BulletBench · measured by Spring Prompt · 5 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| BulletBench Bullet 60s: cost per gameUS dollars, lower is better | $0.0297 | 58 of 71 | GPT-6 Sol (no reasoning) none reasoning |
1 Oct 2026 |
| BulletBench Bullet 60s: games lost on time% of games, lower is better | 50.0% | 41 of 71 | GPT-6 Sol (no reasoning) none reasoning |
1 Oct 2026 |
| BulletBench Bullet 60s: invalid moves% of moves, lower is better | 0.0% | 1 of 71 | GPT-6 Sol (no reasoning) none reasoning |
1 Oct 2026 |
| BulletBench Bullet 60s: ladder Eloladder Elo, higher is better | 445 215–639 |
42 of 71 | GPT-6 Sol (no reasoning) none reasoning |
1 Oct 2026 |
| BulletBench Bullet 60s: median move timemilliseconds, lower is better | 1.6 s | 41 of 71 | GPT-6 Sol (no reasoning) none reasoning |
1 Oct 2026 |
Not shown: Not your cost: prices are those charged on the run date.
CatalogBench · measured by Spring Prompt · 31 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| CatalogBench (sales brief): channel rules broken% of products, lower is better | 0.6% | 17 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): claims to check% of products, lower is better | 0.0% | 1 of 32 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): content quality% of checks, higher is better | 98.3% | 8 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): failed outputs% of products, lower is better | 0.0% | 1 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): missing UK information% of products, lower is better | 0.0% | 1 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): not findable% of products, lower is better | 7.1% | 29 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): publish-ready listings% of products, higher is better | 76.2% | 1 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): reliably publish-ready% of products, higher is better | 67.9% | 2 of 34 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): unsupported claims% of products, lower is better | 3.0% | 4 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): unsupported claimsclaims per product, lower is better | 0.09 | 3 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): wrong attributes% of products, lower is better | 13.7% | 4 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): wrong category or variant% of products, lower is better | 3.0% | 24 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: channel compliance% of products, higher is better | 100.0% | 1 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: channel rules broken% of products, lower is better | 0.0% | 1 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: claims to check% of products, lower is better | 0.0% | 1 of 32 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: conflicts caught% of conflicts, higher is better | 100.0% | 1 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: content quality% of checks, higher is better | 97.8% | 8 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: cost per productUS dollars, lower is better | $0.0085 | 18 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: decision accuracy% of decisions, higher is better | 98.0% | 7 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: failed outputs% of products, lower is better | 0.0% | 1 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: field accuracy% of missing fields, higher is better | 93.7% | 15 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: invented values% of filled values, lower is better | 1.0% | 12 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: missing UK information% of products, lower is better | 0.0% | 1 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: not findable% of products, lower is better | 7.7% | 27 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: publish-ready listings% of products, higher is better | 75.0% | 5 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: reliably publish-ready% of products, higher is better | 66.1% | 4 of 34 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: time per productseconds, lower is better | 10.7 | 13 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: unsupported claims% of products, lower is better | 1.8% | 5 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: unsupported claimsclaims per product, lower is better | 0.08 | 5 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: wrong attributes% of products, lower is better | 14.3% | 8 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
| CatalogBench: wrong category or variant% of products, lower is better | 3.6% | 27 of 35 | GPT-6 Sol provider default reasoning |
30 Sep 2026 |
Not shown: Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
DeckBench · measured by Spring Prompt · 17 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| DeckBench: accurate decks% of tasks, higher is better | 83.3% | 5 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: caveat dropped% of tasks, lower is better | 0.0% | 1 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: clean layout% of tasks, higher is better | 66.7% | 8 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: cost per deckUS dollars, lower is better | $0.21 | 26 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: deck ratingrating, higher is better | 1,456 1,394–1,561 |
3 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: design quality% of the maximum, higher is better | 87.9% | 2 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: draft figure quoted% of tasks, lower is better | 0.0% | 1 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: findings missing% of tasks, lower is better | 16.7% | 23 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: head-to-head win rate% of comparisons, higher is better | 87.5% | 2 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: layout defects% of tasks, lower is better | 33.3% | 8 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: misleading metric used% of tasks, lower is better | 0.0% | 1 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: presentable decks% of tasks, higher is better | 50.0% | 3 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: recommendation late or wrong% of tasks, lower is better | 0.0% | 1 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: slides needing work% of tasks, lower is better | 0.0% | 1 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: time per deckseconds, lower is better | 169 | 20 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: unsupported claims% of tasks, lower is better | 0.0% | 1 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
| DeckBench: unsupported numbers% of tasks, lower is better | 0.0% | 1 of 34 | GPT-6 Sol provider default reasoning |
6 Oct 2026 |
Not shown: Not your analysis or your brand: invented companies, six public tasks, one deck per model per task at the provider's default reasoning setting.
ROASBench · measured by Spring Prompt · 9 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| ROASBench: audience scorescore out of 100, higher is better | 69.4 | 2 of 35 | GPT-6 Sol provider default reasoning |
29 Sep 2026 |
| ROASBench: business scorescore out of 100, higher is better | 52.9 | 8 of 35 | GPT-6 Sol provider default reasoning |
29 Sep 2026 |
| ROASBench: consistency scorescore out of 100, higher is better | 42.9 | 3 of 35 | GPT-6 Sol provider default reasoning |
29 Sep 2026 |
| ROASBench: contribution profitsimulated US dollars, higher is better | $600,357 | 17 of 35 | GPT-6 Sol provider default reasoning |
29 Sep 2026 |
| ROASBench: cost of a runUS dollars, lower is better | $0.24 | 21 of 35 | GPT-6 Sol provider default reasoning |
29 Sep 2026 |
| ROASBench: months over budgetmonths of 12, lower is better | 0 | 1 of 35 | GPT-6 Sol provider default reasoning |
29 Sep 2026 |
| ROASBench: overall scorescore out of 100, higher is better | 54.1 | 5 of 35 | GPT-6 Sol provider default reasoning |
29 Sep 2026 |
| ROASBench: planning scorescore out of 100, higher is better | 54.8 | 16 of 35 | GPT-6 Sol provider default reasoning |
29 Sep 2026 |
| ROASBench: return on ad spendprofit per $1 spent, higher is better | $0.65 | 11 of 35 | GPT-6 Sol provider default reasoning |
29 Sep 2026 |
Not shown: Not real ad performance: the market is a deterministic simulation of one invented skincare brand.
APEX-Agents · reported by APEX-Agents · 1 result
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| APEX-Agents: tasks passed% of tasks, higher is better | 54.3% | 18 of 39 | GPT-6 Sol (max reasoning) | 1 Oct 2026 |
Not shown: Not your firm's documents or tools; graded by rubric, not by a client.
Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 11 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Arena Agent: confirmed task successIPS effect estimate, higher is better | 0.07 0.03–0.11 |
11 of 50 | GPT-6 Sol (max reasoning, arena agent) | 2 Oct 2026 |
| Arena Agent: praise over complaintIPS effect estimate, higher is better | 0.23 0.13–0.33 |
7 of 50 | GPT-6 Sol (max reasoning, arena agent) | 2 Oct 2026 |
| Arena Agent: steerabilityIPS effect estimate, higher is better | 0.11 0.09–0.13 |
2 of 50 | GPT-6 Sol (max reasoning, arena agent) | 2 Oct 2026 |
| Arena Agent: tool groundingIPS effect estimate, higher is better | 0.00 -0.00–0.00 |
32 of 50 | GPT-6 Sol (max reasoning, arena agent) | 2 Oct 2026 |
| Arena Text factuality: overallArena rating, higher is better | 1,434 1,428–1,440 |
104 of 182 | GPT-6 Sol (max reasoning) | 2 Oct 2026 |
| Arena Text: business, management and financeArena rating, higher is better | 1,446 1,431–1,461 |
86 of 406 | GPT-6 Sol (max reasoning) | 2 Oct 2026 |
| Arena Text: creative writingArena rating, higher is better | 1,442 1,427–1,456 |
57 of 411 | GPT-6 Sol (max reasoning) | 2 Oct 2026 |
| Arena Text: expert promptsArena rating, higher is better | 1,498 1,478–1,517 |
47 of 363 | GPT-6 Sol (max reasoning) | 2 Oct 2026 |
| Arena Text: instruction followingArena rating, higher is better | 1,453 1,442–1,464 |
60 of 413 | GPT-6 Sol (max reasoning) | 2 Oct 2026 |
| Arena Text: overallArena rating, higher is better | 1,457 1,450–1,464 |
64 of 413 | GPT-6 Sol (max reasoning) | 2 Oct 2026 |
| Arena Text: writing, literature and languageArena rating, higher is better | 1,439 1,426–1,451 |
71 of 412 | GPT-6 Sol (max reasoning) | 2 Oct 2026 |
Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.
Artificial Analysis · reported by Artificial Analysis · 30 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 42.4 | 46 of 413 | GPT-6 Sol (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 34.2 | 93 of 413 | GPT-6 Sol (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 47.6 | 26 of 413 | GPT-6 Sol (max reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 39.8 | 61 of 413 | GPT-6 Sol (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 28.5 | 125 of 413 | GPT-6 Sol (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 44.2 | 40 of 413 | GPT-6 Sol (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 44.1% | 52 of 419 | GPT-6 Sol (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 34.9% | 123 of 419 | GPT-6 Sol (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 47.9% | 35 of 419 | GPT-6 Sol (max reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 41.0% | 81 of 419 | GPT-6 Sol (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 18.4% | 215 of 419 | GPT-6 Sol (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 46.3% | 43 of 419 | GPT-6 Sol (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 83.7% | 15 of 407 | GPT-6 Sol (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 79.3% | 96 of 407 | GPT-6 Sol (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 83.7% | 15 of 407 | GPT-6 Sol (max reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 82.3% | 37 of 407 | GPT-6 Sol (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 64.0% | 237 of 407 | GPT-6 Sol (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 81.3% | 53 of 407 | GPT-6 Sol (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 54.9% | 58 of 205 | GPT-6 Sol (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 50.2% | 111 of 205 | GPT-6 Sol (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 57.6% | 25 of 205 | GPT-6 Sol (max reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 53.8% | 72 of 205 | GPT-6 Sol (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 47.3% | 133 of 205 | GPT-6 Sol (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 55.1% | 51 of 205 | GPT-6 Sol (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 26.3% | 54 of 204 | GPT-6 Sol (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 9.1% | 99 of 204 | GPT-6 Sol (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 43.9% | 27 of 204 | GPT-6 Sol (max reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 18.7% | 71 of 204 | GPT-6 Sol (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 13.1% | 84 of 204 | GPT-6 Sol (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 30.3% | 48 of 204 | GPT-6 Sol (xhigh reasoning) | 20 Oct 2026 |
Not shown: Not business work, and a blend: read the parts for any one task.
GDP.pdf · reported by GDP.pdf · 1 result
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| GDP.pdf: professional document tasks% of rubric, higher is better | 26.4% | 10 of 49 | GPT-6 Sol (max reasoning) | 1 Oct 2026 |
Not shown: Not your documents; 100 tasks, so small differences are noise.
SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| SimpleQA Verified: correct answers% of questions, higher is better | 60.7% | 14 of 85 | GPT-6 Sol (max reasoning) | 22 Sep 2026 |
Not shown: Not answers grounded in your documents; tests what the model remembers.
UGI Leaderboard · reported by UGI Leaderboard · 12 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| UGI: requested-length error% off the requested word count, lower is better | 4.0% | 32 of 379 | GPT-6 Sol (high reasoning) | 2 Oct 2026 |
| UGI: requested-length error% off the requested word count, lower is better | 5.0% | 41 of 379 | GPT-6 Sol (low reasoning) | 2 Oct 2026 |
| UGI: requested-length error% off the requested word count, lower is better | 4.0% | 32 of 379 | GPT-6 Sol (medium reasoning) | 2 Oct 2026 |
| UGI: requested-length error% off the requested word count, lower is better | 4.0% | 32 of 379 | GPT-6 Sol (xhigh reasoning) | 2 Oct 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.38 | 52 of 379 | GPT-6 Sol (high reasoning) | 2 Oct 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.38 | 59 of 379 | GPT-6 Sol (low reasoning) | 2 Oct 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.38 | 68 of 379 | GPT-6 Sol (medium reasoning) | 2 Oct 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.39 | 40 of 379 | GPT-6 Sol (xhigh reasoning) | 2 Oct 2026 |
| UGI: writing scorescore out of 100, higher is better | 55.6 | 130 of 379 | GPT-6 Sol (high reasoning) | 2 Oct 2026 |
| UGI: writing scorescore out of 100, higher is better | 53.8 | 144 of 379 | GPT-6 Sol (low reasoning) | 2 Oct 2026 |
| UGI: writing scorescore out of 100, higher is better | 53.6 | 146 of 379 | GPT-6 Sol (medium reasoning) | 2 Oct 2026 |
| UGI: writing scorescore out of 100, higher is better | 53.9 | 143 of 379 | GPT-6 Sol (xhigh reasoning) | 2 Oct 2026 |
Not shown: Not other format limits such as character counts or bullet counts.
Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Vectara: answer rate% of documents, higher is better | 100.0% | 1 of 108 | GPT-6 Sol | 22 Sep 2026 |
| Vectara: hallucination rate% of summaries, lower is better | 6.5% | 29 of 108 | GPT-6 Sol | 22 Sep 2026 |
Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.
Vending-Bench 2 · reported by Vending-Bench 2 · 1 result
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Vending-Bench 2: money after a yearUS dollars, higher is better | $14,428 | 2 of 63 | GPT-6 Sol | 1 Oct 2026 |
Not shown: Not a real business; one simulated market with set rules.
Embed a score badge
A badge for its Spring Prompt Score and each of our benchmarks that ranked GPT-6 Sol, from the current results. Paste the code into a page or README; it links back to where the result comes from.
Spring Prompt Score · 4 of 5 benchmarks
<a href="https://springprompt.com/score#openai-gpt-6-sol"><img src="https://springprompt.com/badge/score/openai-gpt-6-sol.svg" alt="GPT-6 Sol is #3 of 32 on the Spring Prompt Score (85 of 100, from 4 of 5 of our benchmarks), measured by Spring Prompt" height="20"></a>
CatalogBench · Reliably publish-ready, factual brief
<a href="https://springprompt.com/benchmarks/catalogbench?focus=openai-gpt-6-sol"><img src="https://springprompt.com/badge/catalogbench/openai-gpt-6-sol.svg" alt="GPT-6 Sol is #4 of 32 on CatalogBench (Reliably publish-ready, factual brief: 66.1%), measured by Spring Prompt" height="20"></a>
DeckBench · Deck rating
<a href="https://springprompt.com/benchmarks/deckbench?focus=openai-gpt-6-sol"><img src="https://springprompt.com/badge/deckbench/openai-gpt-6-sol.svg" alt="GPT-6 Sol is #3 of 33 on DeckBench (Deck rating: 1,456), measured by Spring Prompt" height="20"></a>
ROASBench · Score
<a href="https://springprompt.com/benchmarks/roasbench?focus=openai-gpt-6-sol"><img src="https://springprompt.com/badge/roasbench/openai-gpt-6-sol.svg" alt="GPT-6 Sol is #5 of 33 on ROASBench (Score: 54.1), measured by Spring Prompt" height="20"></a>
BulletBench · Ladder Elo
<a href="https://springprompt.com/benchmarks/bulletbench?focus=openai-gpt-6-sol"><img src="https://springprompt.com/badge/bulletbench/openai-gpt-6-sol.svg" alt="GPT-6 Sol is #38 of 59 on BulletBench (Ladder Elo: 445), measured by Spring Prompt" height="20"></a>
Will GPT-6 Sol work for your product?
Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.
New here? Your email starts a free trial. No credit card needed.