Models / GPT-6.1 Terra
OpenAI
GPT-6.1 Terra
GPT-6.1 Terra is best for marketing planning and product listings; a strong pick at a modest price.
Results 4 Nov 2026 · 95 results · 5 sources
- Price per million tokens
- $1.10 in · $5.50 out
Typical host on OpenRouter, 4 Nov 2026 · compare prices - Speed
- Not measured
- Intelligence Index
- Not measured
- Spring Prompt overall
- 2nd of 29 score 81 of 100 · how it works
- Developer
- OpenAI, based in the US
Weights not published - Released
- Not recorded
no launch date in our tracker or our sources
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 | – | 2nd of 29Claude Opus 5.5 | $2.20 blended, 74th percentilecheapest: Mistral Nemo | – |
| Models priced $1–3 per million tokens | – | 1st of 7leads | sets this group | – |
| Models from developers based in the US | – | 2nd of 18Claude Opus 5.5 | $2.20 blended, 54th 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 | ≈ $0.004 |
| Deck | DeckBench | ≈ $0.067 |
| Survey plan and analysis | SurveyBench | ≈ $0.057 |
| Game of blitz chess | BulletBench | ≈ $0.071 |
How good is it, and for what?
Each use case ranks the available models its benchmarks measured, then those priced $1–3 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-6.1 Terra | Rank among available | Best available |
|---|---|---|---|
| CatalogBenchCatalogBench: reliably publish-ready | 64.3% | 5th of 25 | GPT-6 Astra 75.0% |
| CatalogBenchCatalogBench (sales brief): reliably publish-ready | 67.9% | 2nd of 25 | GPT-6 Astra 69.6% |
Decks from an analysisTurning a finished analysis into a deck you could present as it is
| Benchmark | GPT-6.1 Terra | Rank among available | Best available |
|---|---|---|---|
| DeckBenchDeckBench: deck rating | 1,355 | 7th of 26 | GPT-6 Astra 1,620 |
User surveysPlanning a user survey and reading its results without being misled
| Benchmark | GPT-6.1 Terra | Rank among available | Best available |
|---|---|---|---|
| SurveyBenchSurveyBench: analysis rating | 1,246 | 5th of 15 | Claude Opus 5.5 1,507 |
Marketing planningPlanning a year of ad spend without overspending
| Benchmark | GPT-6.1 Terra | Rank among available | Best available |
|---|---|---|---|
| ROASBenchROASBench: overall score | 58.4 | 1st of 26 | This model |
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls
- tau2-bench: has not measured this model.
- Berkeley Function Calling Leaderboard (BFCL) V4: has not measured this model.
- OpenHands Index: has not measured this model.
- Microsoft STATE-Bench: has not measured this model.
- Artificial Analysis: has not measured this model.
- Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects
- APEX-Agents: has not measured this model.
- GDP.pdf: has not measured this model.
- Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge
- Artificial Analysis: has not measured this model.
WritingWhat people prefer in blind comparisons, and judged writing quality
- Arena (formerly LMArena): has not measured this model.
- UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers
- Vectara Hallucination Leaderboard: has not measured this model.
- Arena (formerly LMArena): has not measured this model.
- SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess)
| Benchmark | GPT-6.1 Terra | Rank among available | Best available |
|---|---|---|---|
| BulletBenchBulletBench Lightning 10+1: ladder Elo | 491 | 11th of 17 | Gemini 3.5 Flash-Lite 892 |
| BulletBenchBulletBench Bullet 60s: ladder Elo | 358 | 16th of 27 | Gemini 3.8 Flash 1,068 |
Nearest alternatives
- The most capable open-weights modelMiMo-V2.6-Pro$0.54 blended · Intelligence Index 46.3
Against GPT-6.1 Terra at $2.20 blended. "Similar intelligence" means within 4 points or better.
Where to run it
5 hosts on OpenRouter at the standard service tier, with a median of $2.20 blended per million tokens. Cheapest first.
| Host | Quantisation | Input | Output | Blended |
|---|---|---|---|---|
| Azure | not stated | $1.00 | $5.00 | $2.00 |
| OpenAI | not stated | $1.00 | $5.00 | $2.00 |
| Amazon Bedrock | not stated | $1.10 | $5.50 | $2.20 |
| Azure | not stated | $1.10 | $5.50 | $2.20 |
| Azure | not stated | $1.20 | $6.00 | $2.40 |
Other service tiers, not counted above: OpenAI fast $2.00 in, $10.00 out; OpenAI flex $0.50 in, $2.50 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 4 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-6.1 Terra | Claude Opus 5.5 highest-scoring overall available today | GPT-6.1 Sol just below overall | |
|---|---|---|---|
| Price per million tokens | $2.20 | $8.00 | $4.00 |
| Tokens a second | – | 96 | 53 |
| Intelligence Index | – | 57.6 | 51.8 |
| Spring Prompt overall | 81 | 83 | 80 |
| Rank among available models, by use case | |||
| Product listings | 4th of 25 | 10th | 2nd |
| Decks from an analysis | 7th of 26 | 4th | 3rd |
| User surveys | 5th of 15 | 1st | 3rd |
| Marketing planning | 1st of 26 | 7th | – |
| Agents and tool use | – | 2nd | 5th |
| Professional work | – | 3rd | 9th |
| Reasoning and knowledge | – | 1st | 6th |
| Writing | – | 5th | 16th |
| Sticking to the facts | – | 3rd | 18th |
| Speed under pressure | 16th of 29 | – | 3rd |
| Side by side → | Side by side → | ||
Shaded figures are better than GPT-6.1 Terra's. A dash means no result.
Where it has been measured
Highest-scoring overall of the 7 models priced $1–3 per million tokens, and 2nd highest-scoring overall of the 18 models from developers based in the US. Among models available today, in the top quarter (by percentile) for marketing planning, product listings and decks from an analysis.
Not timed: Artificial Analysis, our source for speed, has not tested it
- BulletBench15 results
- CatalogBench32 results
- DeckBench18 results
- ROASBench9 results
- SurveyBench21 results
- APEX-AgentsNot measured
- Arena (formerly LMArena)Not measured
- Artificial AnalysisNot measured
- Berkeley Function Calling Leaderboard (BFCL) V4Not measured
- GDP.pdfNot measured
- Microsoft STATE-BenchNot measured
- OpenHands IndexNot measured
- Remote Labor IndexNot measured
- SimpleQA Verified (Epoch AI)Not measured
- tau2-benchNot measured
- UGI LeaderboardNot measured
- Vectara Hallucination LeaderboardNot measured
- Vending-Bench 2Not measured
Every result
95 published results from 5 sources, each in the source's own units, with the configuration that produced it.
BulletBench · measured by Spring Prompt · 15 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| BulletBench Blitz 3+2: cost per gameUS dollars, lower is better | $0.0706 | 7 of 17 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| BulletBench Blitz 3+2: games lost on time% of games, lower is better | 25.0% | 8 of 17 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| BulletBench Blitz 3+2: invalid moves% of moves, lower is better | 0.0% | 1 of 17 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| BulletBench Blitz 3+2: ladder Eloladder Elo, higher is better | 683 487–1,130 |
6 of 17 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| BulletBench Blitz 3+2: median move timemilliseconds, lower is better | 3.7 s | 7 of 17 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| BulletBench Bullet 60s: cost per gameUS dollars, lower is better | $0.0172 | 26 of 42 | GPT-6.1 Terra (low reasoning) low reasoning |
27 Oct 2026 |
| BulletBench Bullet 60s: games lost on time% of games, lower is better | 75.0% | 30 of 42 | GPT-6.1 Terra (low reasoning) low reasoning |
27 Oct 2026 |
| BulletBench Bullet 60s: invalid moves% of moves, lower is better | 0.0% | 1 of 42 | GPT-6.1 Terra (low reasoning) low reasoning |
27 Oct 2026 |
| BulletBench Bullet 60s: ladder Eloladder Elo, higher is better | 358 0–595 |
26 of 42 | GPT-6.1 Terra (low reasoning) low reasoning |
27 Oct 2026 |
| BulletBench Bullet 60s: median move timemilliseconds, lower is better | 2.8 s | 32 of 42 | GPT-6.1 Terra (low reasoning) low reasoning |
27 Oct 2026 |
| BulletBench Lightning 10+1: cost per gameUS dollars, lower is better | $0.0064 | 15 of 27 | GPT-6.1 Terra (low reasoning) low reasoning |
27 Oct 2026 |
| BulletBench Lightning 10+1: games lost on time% of games, lower is better | 62.5% | 20 of 27 | GPT-6.1 Terra (low reasoning) low reasoning |
27 Oct 2026 |
| BulletBench Lightning 10+1: invalid moves% of moves, lower is better | 0.0% | 1 of 27 | GPT-6.1 Terra (low reasoning) low reasoning |
27 Oct 2026 |
| BulletBench Lightning 10+1: ladder Eloladder Elo, higher is better | 491 0–727 |
18 of 27 | GPT-6.1 Terra (low reasoning) low reasoning |
27 Oct 2026 |
| BulletBench Lightning 10+1: median move timemilliseconds, lower is better | 1.3 s | 22 of 27 | GPT-6.1 Terra (low reasoning) low reasoning |
27 Oct 2026 |
Not shown: Not your cost: prices are those charged on the run date.
CatalogBench · measured by Spring Prompt · 32 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| CatalogBench (sales brief): channel rules broken% of products, lower is better | 0.0% | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench (sales brief): claims to check% of products, lower is better | 0.0% | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench (sales brief): content quality% of checks, higher is better | 98.3% | 5 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench (sales brief): failed outputs% of products, lower is better | 0.0% | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench (sales brief): missing UK information% of products, lower is better | 0.0% | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench (sales brief): not findable% of products, lower is better | 13.7% | 26 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench (sales brief): publish-ready listings% of products, higher is better | 74.4% | 3 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench (sales brief): reliably publish-ready% of products, higher is better | 67.9% | 2 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench (sales brief): unsupported claims% of products, lower is better | 1.8% | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench (sales brief): unsupported claimsclaims per product, lower is better | 0.09 | 3 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench (sales brief): wrong attributes% of products, lower is better | 14.9% | 7 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench (sales brief): wrong category or variant% of products, lower is better | 1.8% | 5 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: channel compliance% of products, higher is better | 98.2% | 25 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: channel rules broken% of products, lower is better | 1.8% | 23 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: claims to check% of products, lower is better | 0.0% | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: conflicts caught% of conflicts, higher is better | 100.0% | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: content quality% of checks, higher is better | 97.7% | 9 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: cost per productUS dollars, lower is better | $0.0036 | 7 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: decision accuracy% of decisions, higher is better | 98.1% | 5 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: failed outputs% of products, lower is better | 0.0% | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: field accuracy% of missing fields, higher is better | 94.4% | 6 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: invented values% of filled values, lower is better | 1.5% | 12 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: missing UK information% of products, lower is better | 0.0% | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: not findable% of products, lower is better | 10.7% | 24 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: output tokens per producttokens, lower is better | 457 | 1 of 4 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: publish-ready listings% of products, higher is better | 74.4% | 6 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: reliably publish-ready% of products, higher is better | 64.3% | 5 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: time per productseconds, lower is better | 10.1 | 9 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: unsupported claims% of products, lower is better | 0.6% | 3 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: unsupported claimsclaims per product, lower is better | 0.03 | 4 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: wrong attributes% of products, lower is better | 14.9% | 5 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| CatalogBench: wrong category or variant% of products, lower is better | 1.8% | 5 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 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 · 18 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| DeckBench: accurate decks% of tasks, higher is better | 100.0% | 1 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: caveat dropped% of tasks, lower is better | 0.0% | 1 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: clean layout% of tasks, higher is better | 83.3% | 3 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: cost per deckUS dollars, lower is better | $0.0672 | 13 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: deck ratingrating, higher is better | 1,355 1,256–1,458 |
7 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: design quality% of the maximum, higher is better | 80.8% | 5 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: draft figure quoted% of tasks, lower is better | 0.0% | 1 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: findings missing% of tasks, lower is better | 0.0% | 1 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: head-to-head win rate% of comparisons, higher is better | 48.3% | 15 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: layout defects% of tasks, lower is better | 16.7% | 3 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: misleading metric used% of tasks, lower is better | 0.0% | 1 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: output tokens per decktokens, lower is better | 12,086 | 1 of 5 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: presentable decks% of tasks, higher is better | 50.0% | 2 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: recommendation late or wrong% of tasks, lower is better | 0.0% | 1 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: slides needing work% of tasks, lower is better | 33.3% | 8 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: time per deckseconds, lower is better | 135 | 16 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: unsupported claims% of tasks, lower is better | 0.0% | 1 of 26 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| DeckBench: unsupported numbers% of tasks, lower is better | 0.0% | 1 of 26 | GPT-6.1 Terra provider default reasoning |
27 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 | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| ROASBench: business scorescore out of 100, higher is better | 59.1 | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| ROASBench: consistency scorescore out of 100, higher is better | 48.8 | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| ROASBench: contribution profitsimulated US dollars, higher is better | $701,059 | 6 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| ROASBench: cost of a runUS dollars, lower is better | $0.11 | 9 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| ROASBench: months over budgetmonths of 12, lower is better | 0 | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| ROASBench: overall scorescore out of 100, higher is better | 58.4 | 1 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| ROASBench: planning scorescore out of 100, higher is better | 55.0 | 7 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| ROASBench: return on ad spendprofit per $1 spent, higher is better | $0.71 | 2 of 27 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
Not shown: Not real ad performance: the market is a deterministic simulation of one invented skincare brand.
SurveyBench · measured by Spring Prompt · 21 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| SurveyBench: analysis ratingrating, higher is better | 1,246 1,147–1,351 |
5 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: analysis scorepoints of 100, higher is better | 91.6 | 4 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: cost per taskUS dollars, lower is better | $0.0569 | 5 of 14 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: head-to-head win rate% of comparisons, higher is better | 56.2% | 6 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: leading or double-barrelled questions% of tasks, lower is better | 11.1% | 3 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: mistaken next steps% of tasks, lower is better | 11.1% | 4 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: numbers right% of answers, higher is better | 100.0% | 1 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: objectives unanswerable% of tasks, lower is better | 11.1% | 8 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: output tokens per tasktokens, lower is better | 8,112 | 1 of 4 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: precision ignored% of tasks, lower is better | 0.0% | 1 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: research scorepoints of 100, higher is better | 92.2 | 4 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: sound research% of tasks, higher is better | 33.3% | 3 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: stakeholder's view presumed% of tasks, lower is better | 11.1% | 6 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: survey plan scorepoints of 100, higher is better | 93.6 | 5 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: survey structure% of tasks, lower is better | 22.2% | 8 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: time per taskseconds, lower is better | 92.1 | 5 of 14 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: traps handled% of traps, higher is better | 94.2% | 4 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: traps missed% of tasks, lower is better | 33.3% | 3 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: unsupported findings% of tasks, lower is better | 0.0% | 1 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: wrong numbers% of tasks, lower is better | 0.0% | 1 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
| SurveyBench: wrong recommendation% of tasks, lower is better | 11.1% | 3 of 15 | GPT-6.1 Terra provider default reasoning |
27 Oct 2026 |
Not shown: Not your customers or your data: invented organisations with simulated respondents, nine public tasks, one run per model per task at the provider's default reasoning setting.