Compare / Claude Haiku 4.5 vs GPT-6.1 Terra
Claude Haiku 4.5 vs GPT-6.1 Terra
Which is cheaper, which is more capable, and which does better at each kind of work, from 92 results on 5 sources that measured both models.
AnthropicClaude Haiku 4.5
OpenAIGPT-6.1 Terra
Claude Haiku 4.5 wins 1512 too close to callGPT-6.1 Terra wins 65
Of the 92 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 4 November 2026 (catalogue release 2026-11-04-56cfea57899a). See also Anthropic vs OpenAI, every model from both labs.
Claude Haiku 4.5 or GPT-6.1 Terra? The short answer
Pick GPT-6.1 Terra: it scores higher (Spring Prompt overall 81 against 7) and costs less.
- Spring Prompt overall: Claude Haiku 4.5 7, GPT-6.1 Terra 81 (out of 100; how the score works).
- GPT-6.1 Terra is cheaper to run: $0.004 against $0.006 per product listing on CatalogBench (42% less).
- On our own benchmarks, on the results both models have: GPT-6.1 Terra does better for product listings, decks from an analysis, user surveys and marketing planning.
Head to head
7
Spring Prompt overall
81
$2.00
Price per million tokens, blendedlower is better
$2.20
200,000
Context window, tokens
1,050,000
Every fact side by side
| Claude Haiku 4.5 | GPT-6.1 Terra | |
|---|---|---|
| Price per million tokens | $1.00 in · $5.00 out | $1.10 in · $5.50 out |
| Blended (3 in : 1 out) | $2.00 | $2.20 |
| Cheapest host, blended | $2.00 (Amazon Bedrock) | $2.00 (Azure) |
| Cost per product listing (CatalogBench) | $0.006 | $0.004 |
| Cached input, per million | $0.10 cached input | – |
| Intelligence Index | 16.9 | – |
| Spring Prompt overall | 7 | 81 |
| Output speed, tokens a second | – | – |
| Context window | 200,000 tokens | 1,050,000 tokens |
| Released | 15 Oct 2025 | – |
| 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.
Product listingsTurning a sparse product feed and photos into listings that can go live
24 of 25
4 of 25
Decks from an analysisTurning a finished analysis into a deck you could present as it is
22 of 26
7 of 26
User surveysPlanning a user survey and reading its results without being misled
14 of 15
5 of 15
Marketing planningPlanning a year of ad spend without overspending
25 of 26
1 of 26
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls
96 of 160
not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge
125 of 188
not measured
WritingWhat people prefer in blind comparisons, and judged writing quality
86 of 173
not measured
Sticking to the factsSummarising without inventing things, and factual answers
111 of 143
not measured
Speed under pressureGood decisions against a real clock (fast chess)
20 of 29
16 of 29
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 | Claude Haiku 4.5 | GPT-6.1 Terra |
|---|---|---|
| BulletBench measured by Spring Prompt · 3 results | ||
| Cost per game · Blitz 3+2US dollars, lower is better 6 · 7 of 16 measured | $0.0318 | $0.0706 |
| Cost per game · Bullet 60sUS dollars, lower is better 23 · 24 of 34 measured | $0.0163 | $0.0172low reasoning |
| Ladder Elo · Bullet 60sladder Elo, higher is better 18 · 23 of 34 measured | 445 | 358low reasoning |
| CatalogBench measured by Spring Prompt · 3 results | ||
| Cost per productUS dollars, lower is better 9 · 7 of 26 measured | $0.0061 | $0.0036 |
| Reliably publish-ready% of products, higher is better 24 · 5 of 25 measured | 1.8% | 64.3% |
| Reliably publish-ready · sales brief% of products, higher is better 22 · 2 of 25 measured | 0.0% | 67.9% |
| DeckBench measured by Spring Prompt · 3 results | ||
| Cost per deckUS dollars, lower is better 9 · 13 of 26 measured | $0.0461 | $0.0672 |
| 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. 22 · 7 of 26 measured | 698 | 1,355 |
| Accurate decks% of tasks, higher is better 19 · 1 of 26 measured | 16.7% | 100.0% |
| ROASBench measured by Spring Prompt · 3 results | ||
| Overall scorescore out of 100, higher is better 25 · 1 of 26 measured | 17.5 | 58.4 |
| Audience scorescore out of 100, higher is better 25 · 1 of 26 measured | 30.9 | 69.4 |
| Business scorescore out of 100, higher is better 25 · 1 of 26 measured | 7.3 | 59.1 |
| SurveyBench measured by Spring Prompt · 3 results | ||
| Analysis ratingrating, higher is betterThe rating weighs each win by how strong the other analysis was; the win rate counts wins against whichever analyses a model happened to meet, so the two can disagree. 14 · 5 of 15 measured | 588 | 1,246 |
| Cost per taskUS dollars, lower is better 6 · 5 of 14 measured | $0.0635 | $0.0569 |
| Analysis scorepoints of 100, higher is better 10 · 4 of 15 measured | 56.8 | 91.6 |
Show all 92 results (77 more)
| Measure | Claude Haiku 4.5 | GPT-6.1 Terra |
|---|---|---|
| BulletBench measured by Spring Prompt · 12 results | ||
| Ladder Elo · Lightning 10+1ladder Elo, higher is better 22 · 17 of 25 measured | 33 | 491low reasoning |
| Cost per game · Lightning 10+1US dollars, lower is better 20 · 15 of 25 measured | $0.0095 | $0.0064low reasoning |
| Games lost on time · Blitz 3+2% of games, lower is better 1 · 8 of 16 measured | 0.0% | 25.0% |
| Games lost on time · Bullet 60s% of games, lower is better 14 · 27 of 34 measured | 25.0% | 75.0%low reasoning |
| Games lost on time · Lightning 10+1% of games, lower is better 22 · 19 of 25 measured | 83.3% | 62.5%low reasoning |
| Invalid moves · Blitz 3+2% of moves, lower is better 16 · 1 of 16 measured | 0.9% | 0.0% |
| Invalid moves · Bullet 60s% of moves, lower is better 28 · 1 of 34 measured | 0.3% | 0.0%low reasoning |
| Invalid moves · Lightning 10+1% of moves, lower is better 1 · 1 of 25 measured | 0.0% | 0.0%low reasoning |
| Ladder Elo · Blitz 3+2ladder Elo, higher is better 14 · 6 of 16 measured | 491 | 683 |
| Median move time · Blitz 3+2milliseconds, lower is better 4 · 7 of 16 measured | 1.3 s | 3.7 s |
| Median move time · Bullet 60smilliseconds, lower is better 18 · 29 of 34 measured | 1.2 s | 2.8 slow reasoning |
| Median move time · Lightning 10+1milliseconds, lower is better 22 · 21 of 25 measured | 1.3 s | 1.3 slow reasoning |
| CatalogBench measured by Spring Prompt · 28 results | ||
| Channel compliance% of products, higher is better 1 · 25 of 26 measured | 100.0% | 98.2% |
| Channel rules broken% of products, lower is better 1 · 23 of 26 measured | 0.0% | 1.8% |
| Channel rules broken · sales brief% of products, lower is better 26 · 1 of 26 measured | 4.2% | 0.0% |
| Claims to check% of products, lower is better 26 · 1 of 26 measured | 22.6% | 0.0% |
| Claims to check · sales brief% of products, lower is better 26 · 1 of 26 measured | 44.6% | 0.0% |
| Conflicts caught% of conflicts, higher is better 1 · 1 of 26 measured | 100.0% | 100.0% |
| Content quality% of checks, higher is better 23 · 9 of 26 measured | 94.4% | 97.7% |
| Content quality · sales brief% of checks, higher is better 24 · 5 of 26 measured | 93.9% | 98.3% |
| Decision accuracy% of decisions, higher is better 25 · 5 of 26 measured | 90.6% | 98.1% |
| Failed outputs% of products, lower is better 1 · 1 of 26 measured | 0.0% | 0.0% |
| Failed outputs · sales brief% of products, lower is better 1 · 1 of 26 measured | 0.0% | 0.0% |
| Field accuracy% of missing fields, higher is better 12 · 6 of 26 measured | 93.7% | 94.4% |
| Invented values% of filled values, lower is better 26 · 12 of 26 measured | 6.2% | 1.5% |
| Missing UK information% of products, lower is better 1 · 1 of 26 measured | 0.0% | 0.0% |
| Missing UK information · sales brief% of products, lower is better 1 · 1 of 26 measured | 0.0% | 0.0% |
| Not findable% of products, lower is better 21 · 23 of 26 measured | 8.9% | 10.7% |
| Not findable · sales brief% of products, lower is better 19 · 25 of 26 measured | 6.6% | 13.7% |
| Publish-ready listings% of products, higher is better 25 · 6 of 26 measured | 12.5% | 74.4% |
| Publish-ready listings · sales brief% of products, higher is better 25 · 3 of 26 measured | 3.0% | 74.4% |
| Time per productseconds, lower is better 5 · 9 of 26 measured | 8.10 | 10.1 |
| Unsupported claimsclaims per product, lower is better 26 · 4 of 26 measured | 2.69 | 0.03 |
| Unsupported claims% of products, lower is better 26 · 3 of 26 measured | 73.2% | 0.6% |
| Unsupported claims · sales brief% of products, lower is better 26 · 1 of 26 measured | 91.7% | 1.8% |
| Unsupported claims · sales briefclaims per product, lower is better 26 · 3 of 26 measured | 5.32 | 0.09 |
| Wrong attributes% of products, lower is better 26 · 5 of 26 measured | 48.2% | 14.9% |
| Wrong attributes · sales brief% of products, lower is better 26 · 7 of 26 measured | 51.2% | 14.9% |
| Wrong category or variant% of products, lower is better 24 · 5 of 26 measured | 7.7% | 1.8% |
| Wrong category or variant · sales brief% of products, lower is better 24 · 5 of 26 measured | 6.6% | 1.8% |
| DeckBench measured by Spring Prompt · 14 results | ||
| Caveat dropped% of tasks, lower is better 1 · 1 of 26 measured | 0.0% | 0.0% |
| Clean layout% of tasks, higher is better 13 · 3 of 26 measured | 50.0% | 83.3% |
| Design quality% of the maximum, higher is better 22 · 5 of 26 measured | 47.6% | 80.8% |
| Draft figure quoted% of tasks, lower is better 21 · 1 of 26 measured | 50.0% | 0.0% |
| Findings missing% of tasks, lower is better 18 · 1 of 26 measured | 16.7% | 0.0% |
| 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. 22 · 15 of 26 measured | 31.3% | 48.3% |
| Layout defects% of tasks, lower is better 13 · 3 of 26 measured | 50.0% | 16.7% |
| Misleading metric used% of tasks, lower is better 1 · 1 of 26 measured | 0.0% | 0.0% |
| Presentable decks% of tasks, higher is better 13 · 2 of 26 measured | 0.0% | 50.0% |
| Recommendation late or wrong% of tasks, lower is better 19 · 1 of 26 measured | 50.0% | 0.0% |
| Slides needing work% of tasks, lower is better 18 · 8 of 26 measured | 66.7% | 33.3% |
| Time per deckseconds, lower is better 4 · 16 of 26 measured | 51.7 | 135 |
| Unsupported claims% of tasks, lower is better 19 · 1 of 26 measured | 33.3% | 0.0% |
| Unsupported numbers% of tasks, lower is better 1 · 1 of 26 measured | 0.0% | 0.0% |
| ROASBench measured by Spring Prompt · 6 results | ||
| Consistency scorescore out of 100, higher is better 25 · 1 of 26 measured | 8.7 | 48.8 |
| Contribution profitsimulated US dollars, higher is better 26 · 6 of 26 measured | −$205,001 | $701,059 |
| Cost of a runUS dollars, lower is better 3 · 9 of 26 measured | $0.0298 | $0.11 |
| Months over budgetmonths of 12, lower is better 24 · 1 of 26 measured | 2 | 0 |
| Planning scorescore out of 100, higher is better 21 · 7 of 26 measured | 54.4 | 55.0 |
| Return on ad spendprofit per $1 spent, higher is better 26 · 2 of 26 measured | −$0.21 | $0.71 |
| SurveyBench measured by Spring Prompt · 17 results | ||
| Head-to-head win rate% of comparisons, higher is betterThe rating weighs each win by how strong the other analysis was; the win rate counts wins against whichever analyses a model happened to meet, so the two can disagree. 14 · 6 of 15 measured | 23.9% | 56.2% |
| Leading or double-barrelled questions% of tasks, lower is better 12 · 3 of 15 measured | 66.7% | 11.1% |
| Mistaken next steps% of tasks, lower is better 11 · 4 of 15 measured | 55.6% | 11.1% |
| Numbers right% of answers, higher is better 14 · 1 of 15 measured | 63.7% | 100.0% |
| Objectives unanswerable% of tasks, lower is better 13 · 8 of 15 measured | 22.2% | 11.1% |
| Precision ignored% of tasks, lower is better 13 · 1 of 15 measured | 100.0% | 0.0% |
| Research scorepoints of 100, higher is better 10 · 4 of 15 measured | 64.9 | 92.2 |
| Sound research% of tasks, higher is better 7 · 3 of 15 measured | 0.0% | 33.3% |
| Stakeholder's view presumed% of tasks, lower is better 9 · 6 of 15 measured | 22.2% | 11.1% |
| Survey plan scorepoints of 100, higher is better 11 · 5 of 15 measured | 83.6 | 93.6 |
| Survey structure% of tasks, lower is better 1 · 8 of 15 measured | 0.0% | 22.2% |
| Time per taskseconds, lower is better 6 · 5 of 14 measured | 92.6 | 92.1 |
| Traps handled% of traps, higher is better 12 · 4 of 15 measured | 62.3% | 94.2% |
| Traps missed% of tasks, lower is better 8 · 3 of 15 measured | 88.9% | 33.3% |
| Unsupported findings% of tasks, lower is better 12 · 1 of 15 measured | 100.0% | 0.0% |
| Wrong numbers% of tasks, lower is better 13 · 1 of 15 measured | 100.0% | 0.0% |
| Wrong recommendation% of tasks, lower is better 9 · 3 of 15 measured | 44.4% | 11.1% |
Compare them with other models
- Anthropic vs OpenAIEvery model from both labs, best against best
- Claude Haiku 4.5 vs Muse Spark 1.3Most intelligent at $1–3 per million tokens
- Claude Haiku 4.5 vs Claude Opus 5.5Most intelligent available today
- GPT-6.1 Terra vs Claude Opus 5.5Highest-scoring overall available today
- GPT-6.1 Terra vs GPT-6.1 SolJust below overall
Quick answers
Is Claude Haiku 4.5 better than GPT-6.1 Terra?
Pick GPT-6.1 Terra: it scores higher (Spring Prompt overall 81 against 7) and costs less.
Which is cheaper, Claude Haiku 4.5 or GPT-6.1 Terra?
GPT-6.1 Terra is cheaper to run: $0.004 against $0.006 per product listing on CatalogBench (42% less).
Which is better for product listings, Claude Haiku 4.5 or GPT-6.1 Terra?
GPT-6.1 Terra ranks 4 of 25 models on sale for turning a sparse product feed and photos into listings that can go live, against 24 for Claude Haiku 4.5.
Which is better for decks from an analysis, Claude Haiku 4.5 or GPT-6.1 Terra?
GPT-6.1 Terra ranks 7 of 26 models on sale for turning a finished analysis into a deck you could present as it is, against 22 for Claude Haiku 4.5.
Which is better for user surveys, Claude Haiku 4.5 or GPT-6.1 Terra?
GPT-6.1 Terra ranks 5 of 15 models on sale for planning a user survey and reading its results without being misled, against 14 for Claude Haiku 4.5.
Which is better for marketing planning, Claude Haiku 4.5 or GPT-6.1 Terra?
GPT-6.1 Terra ranks 1 of 26 models on sale for planning a year of ad spend without overspending, against 25 for Claude Haiku 4.5.
Which is better for speed under pressure, Claude Haiku 4.5 or GPT-6.1 Terra?
GPT-6.1 Terra ranks 16 of 29 models on sale for good decisions against a real clock (fast chess), against 20 for Claude Haiku 4.5.
Which has the bigger context window, Claude Haiku 4.5 or GPT-6.1 Terra?
GPT-6.1 Terra: 1,050,000 tokens, against 200,000 for Claude Haiku 4.5.
Run Claude Haiku 4.5 and GPT-6.1 Terra on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.