Claude Haiku 5.5vs.GPT-6.1 Terra
Which one is better?
Level in the overall index: the gap is too small for a clear winner. Claude Haiku 5.5 is cheaper: GPT-6.1 Terra costs 10 times as much per token.
57
Claude Haiku 5.5
Rank 16 to 27
67
GPT-6.1 Terra
Rank 12 to 27
241
Claude Haiku 5.5
fast
91
GPT-6.1 Terra
fairly slow
$0.20
Claude Haiku 5.5
cheap
$2
GPT-6.1 Terra
fairly expensive
Claude Haiku 5.5
- Subscription
Free to use at Anthropic (Claude Free), more from €21.42 a month (Claude Pro). Through other providers from €6.83 a month (Poe Basic, with limited points). 29 plans in Germany.
- Via API
$0.10 input, $0.50 output per 1M tokens, unchanged since Oct 14, 2026.
GPT-6.1 Terra
- Subscription
Subscriptions in Germany: n/a
- Via API
$1 input, $5 output per 1M tokens.
Overall index with data through Oct 29, 2026 · Prices from Oct 29, 2026 · Speed: measured by Artificial Analysis · Subscriptions as of Oct 24, 2026 · Subscription prices incl. VAT
Where is the difference?
Values from 0 to 100 per task area. We only name a winner when the gap is large enough and there are enough tests.
Haiku 5.5 ahead: 0GPT-6.1 Terra ahead: 3level: 3too little data: 4of 10 areas
AreaHaiku 5.5GPT-6.1 Terra0 to 100, higher is betterResult
Areas in the overall index
CodingGPT-6.1 Terra aheadHaiku 5.5: 66GPT-6.1 Terra: 84
ReasoningGPT-6.1 Terra aheadHaiku 5.5: 62GPT-6.1 Terra: 88
Mathematicsonly Haiku 5.5 has a scoreHaiku 5.5: 69GPT-6.1 Terra: not enough data
KnowledgeGPT-6.1 Terra aheadHaiku 5.5: 10GPT-6.1 Terra: 80
AgentslevelHaiku 5.5: 63GPT-6.1 Terra: 57
Generalonly Haiku 5.5 has a scoreHaiku 5.5: 67GPT-6.1 Terra: not enough data
Multimodalonly GPT-6.1 Terra has a scoreHaiku 5.5: not enough dataGPT-6.1 Terra: 70
Specialist fields
FinancelevelHaiku 5.5: 61GPT-6.1 Terra: 45
LegallevelHaiku 5.5: 30GPT-6.1 Terra: 8
Healthonly Haiku 5.5 has a scoreHaiku 5.5: 76GPT-6.1 Terra: not enough data
Show 3 more areas that do not count toward the overall index
AreaHaiku 5.5GPT-6.1 Terra0 to 100, higher is betterResult
Cybersecurityonly Haiku 5.5 has a scoreHaiku 5.5: 79GPT-6.1 Terra: not enough data
Productivityonly Haiku 5.5 has a scoreHaiku 5.5: 50GPT-6.1 Terra: not enough data
Educationonly Haiku 5.5 has a scoreHaiku 5.5: 79GPT-6.1 Terra: not enough data
See for yourself: same task, one attempt
There is no shared test round for this selection. Results from different rounds are not mixed.
All data side by side
The better value is bold. For the overall index only when the gap is clear.
| Metric | Claude Haiku 5.5 | GPT-6.1 Terra |
|---|---|---|
| Intelligence | ||
| Overall index0 to 100, higher is better | 57 | 67 |
| Rank | Rank 16 to 27 of 95 | Rank 12 to 27 of 95 |
| Price per 1M tokens | ||
| Inputwhat you send | $0.10above 100,000 tokens: $0.50 | $1above 272,000 tokens: $2 |
| Outputwhat the model writes | $0.50above 100,000 tokens: $2.50 | $5above 272,000 tokens: $7.50 |
| Speed | ||
| Tokens per second | 241 | 91 |
| Technical | ||
| Context windowhow much text the model reads at once | 1 M tokens≈ 1,500 A4 pages | 1.05 M tokens≈ 1,580 A4 pages |
| Knowledge cutoff | June 2026 | Jun 1, 2026 |
| Released | Oct 7, 2026 | Oct 26, 2026 |
| Availability | Active | Active |
| Open weights | no | no |
- GPT-6.1 Terra, 12-hour cache write: The table's cache-write rate covers 30-minute retention. With 12-hour retention it is $2.50 per 1M tokens through 272,000 input tokens, $5 above. Source
- GPT-6.1 Terra, Long-context billing: Above 272,000 input tokens, the higher rates apply to the entire request. Input and cache rates double, while output costs 1.5 times the standard rate. Source
- GPT-6.1 Terra, Batch and Flex pricing: 50% off standard pricing Source
- GPT-6.1 Terra, Fast pricing: Fast mode costs twice the standard price Source
- GPT-6.1 Terra, Regional processing: 10% surcharge over standard processing Source
Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis
Shared benchmarks
Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.
A: Claude Haiku 5.5B: GPT-6.1 Terra
AA-BriefcaseOverall · higher is betterClaude Haiku 5.5: 1,439.57 eloGPT-6.1 Terra: 1,263.5 eloArtificial AnalysisAs of 10/29/2026
AA-OmniscienceOverall · higher is betterClaude Haiku 5.5: 5.3 pointsGPT-6.1 Terra: 27.767 pointsArtificial AnalysisAs of 10/29/2026
AA-Omniscience AccuracyOverall · higher is betterClaude Haiku 5.5: 31.8%GPT-6.1 Terra: 47.3%Artificial AnalysisAs of 10/29/2026
AA-Omniscience Hallucination RateOverall · lower is betterClaude Haiku 5.5: 38.9%GPT-6.1 Terra: 37.0%Artificial AnalysisAs of 10/29/2026
Artificial Analysis Intelligence IndexOverall · higher is betterClaude Haiku 5.5: 29.624 pointsGPT-6.1 Terra: 42.334 pointsArtificial AnalysisAs of 10/29/2026
AutomationBench-AAOverall · higher is betterClaude Haiku 5.5: 33.7%GPT-6.1 Terra: 58.5%Artificial AnalysisAs of 10/29/2026
CritPt v2Overall · higher is betterClaude Haiku 5.5: 18.6%GPT-6.1 Terra: 25.7%Artificial AnalysisAs of 10/29/2026
CritPt v2 (Hard Subset)Overall · higher is betterClaude Haiku 5.5: 42.5%GPT-6.1 Terra: 60.5%Artificial AnalysisAs of 10/29/2026
EMB v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 65.5%GPT-6.1 Terra: 73.3%Vals AIAs of 10/26/2026
Finance Agent v2.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 65.4%GPT-6.1 Terra: 56%Vals AIAs of 10/26/2026
Show 54 more benchmarks
FrontierCodeOverall · higher is betterClaude Haiku 5.5: 23.2%GPT-6.1 Terra: 37.5%Artificial AnalysisAs of 10/29/2026
FrontierCode 1.1 MainOverall · higher is betterClaude Haiku 5.5: 43.6%GPT-6.1 Terra: 37.2%Artificial AnalysisAs of 10/29/2026
GDP.pdfOverall · higher is betterClaude Haiku 5.5: 17.2%GPT-6.1 Terra: 28.0%Artificial AnalysisAs of 10/29/2026
GDPval-AAOverall · higher is betterClaude Haiku 5.5: 1,424.51 eloGPT-6.1 Terra: 1,353.15 eloArtificial AnalysisAs of 10/29/2026
HLAB-Vals-1.1Overall · Task fully resolved · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 4.2%GPT-6.1 Terra: 1.7%Vals AIAs of 10/26/2026
HLE-DiamondOverall · higher is betterClaude Haiku 5.5: 23.7%GPT-6.1 Terra: 35.4%Artificial AnalysisAs of 10/29/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 43.8%GPT-6.1 Terra: 26%Vals AIAs of 10/26/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 31.9%GPT-6.1 Terra: 15.2%Vals AIAs of 10/26/2026
Terminal-BenchOverall · higher is betterClaude Haiku 5.5: 21.7%GPT-6.1 Terra: 41.9%Artificial AnalysisAs of 10/29/2026
Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 36.4%GPT-6.1 Terra: 49.5%Vals AIAs of 10/26/2026
Terminal-Bench-ScienceOverall · higher is betterClaude Haiku 5.5: 10.0%GPT-6.1 Terra: 33.3%Artificial AnalysisAs of 10/29/2026
Vals Finance IndexOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 57.4%GPT-6.1 Terra: 52.9%Vals AIAs of 10/26/2026
Vals IndexOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 58.7%GPT-6.1 Terra: 60.5%Vals AIAs of 10/27/2026
Vals Legal IndexOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 70.3%GPT-6.1 Terra: 58.6%Vals AIAs of 10/26/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 90.4%GPT-6.1 Terra: 84%Vals AIAs of 10/26/2026
AA-BriefcaseOverall · higher is betterClaude Haiku 5.5: 1,524.29 eloGPT-6.1 Terra: 1,332.9 eloArtificial AnalysisAs of 10/29/2026
AA-OmniscienceOverall · higher is betterClaude Haiku 5.5: 7.833 pointsGPT-6.1 Terra: 28.933 pointsArtificial AnalysisAs of 10/29/2026
AA-Omniscience AccuracyOverall · higher is betterClaude Haiku 5.5: 33.8%GPT-6.1 Terra: 48.0%Artificial AnalysisAs of 10/29/2026
AA-Omniscience Hallucination RateOverall · lower is betterClaude Haiku 5.5: 39.2%GPT-6.1 Terra: 36.8%Artificial AnalysisAs of 10/29/2026
Artificial Analysis Intelligence IndexOverall · higher is betterClaude Haiku 5.5: 34.339 pointsGPT-6.1 Terra: 44.95 pointsArtificial AnalysisAs of 10/29/2026
AutomationBench-AAOverall · higher is betterClaude Haiku 5.5: 36.0%GPT-6.1 Terra: 59.9%Artificial AnalysisAs of 10/29/2026
CritPt v2Overall · higher is betterClaude Haiku 5.5: 22.6%GPT-6.1 Terra: 26.6%Artificial AnalysisAs of 10/29/2026
CritPt v2 (Hard Subset)Overall · higher is betterClaude Haiku 5.5: 44.5%GPT-6.1 Terra: 57.5%Artificial AnalysisAs of 10/29/2026
EMB v1.1Comps · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 77.7%GPT-6.1 Terra: 75.6%Vals AIAs of 10/26/2026
Finance Agent v2.1Adjustments · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 67.7%GPT-6.1 Terra: 50.6%Vals AIAs of 10/26/2026
FrontierCodeOverall · higher is betterClaude Haiku 5.5: 29.9%GPT-6.1 Terra: 36.9%Artificial AnalysisAs of 10/29/2026
FrontierCode 1.1 MainOverall · higher is betterClaude Haiku 5.5: 45.5%GPT-6.1 Terra: 41.4%Artificial AnalysisAs of 10/29/2026
GDP.pdfOverall · higher is betterClaude Haiku 5.5: 18.2%GPT-6.1 Terra: 26.6%Artificial AnalysisAs of 10/29/2026
GDPval-AAOverall · higher is betterClaude Haiku 5.5: 1,520.97 eloGPT-6.1 Terra: 1,415.29 eloArtificial AnalysisAs of 10/29/2026
HLAB-Vals-1.1Antitrust Competition · Criteria passed · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 86.2%GPT-6.1 Terra: 83%Vals AIAs of 10/26/2026
HLE-DiamondOverall · higher is betterClaude Haiku 5.5: 28.8%GPT-6.1 Terra: 42.3%Artificial AnalysisAs of 10/29/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 50%GPT-6.1 Terra: 45.5%Vals AIAs of 10/26/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 6.7%GPT-6.1 Terra: 5.9%Vals AIAs of 10/26/2026
Terminal-BenchOverall · higher is betterClaude Haiku 5.5: 29.3%GPT-6.1 Terra: 46.5%Artificial AnalysisAs of 10/29/2026
Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 20%GPT-6.1 Terra: 26.7%Vals AIAs of 10/26/2026
Terminal-Bench-ScienceOverall · higher is betterClaude Haiku 5.5: 18.1%GPT-6.1 Terra: 41.9%Artificial AnalysisAs of 10/29/2026
Vals Finance IndexEMB v1.1 · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 65.5%GPT-6.1 Terra: 73.3%Vals AIAs of 10/26/2026
Vals IndexCode Migration v1.1 · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 50.2%GPT-6.1 Terra: 72.2%Vals AIAs of 10/27/2026
Vals Legal IndexBusiness & Commercial · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 67.1%GPT-6.1 Terra: 51.6%Vals AIAs of 10/26/2026
AA-BriefcaseOverall · higher is betterClaude Haiku 5.5: 1,113.51 eloGPT-6.1 Terra: 1,029.93 eloArtificial AnalysisAs of 10/29/2026
AA-OmniscienceOverall · higher is betterClaude Haiku 5.5: 2.167 pointsGPT-6.1 Terra: 22.933 pointsArtificial AnalysisAs of 10/29/2026
AA-Omniscience AccuracyOverall · higher is betterClaude Haiku 5.5: 30.4%GPT-6.1 Terra: 45.6%Artificial AnalysisAs of 10/29/2026
AA-Omniscience Hallucination RateOverall · lower is betterClaude Haiku 5.5: 40.5%GPT-6.1 Terra: 41.6%Artificial AnalysisAs of 10/29/2026
Artificial Analysis Intelligence IndexOverall · higher is betterClaude Haiku 5.5: 18.618 pointsGPT-6.1 Terra: 29.217 pointsArtificial AnalysisAs of 10/29/2026
AutomationBench-AAOverall · higher is betterClaude Haiku 5.5: 22.9%GPT-6.1 Terra: 56.2%Artificial AnalysisAs of 10/29/2026
CritPt v2Overall · higher is betterClaude Haiku 5.5: 9.1%GPT-6.1 Terra: 15.1%Artificial AnalysisAs of 10/29/2026
CritPt v2 (Hard Subset)Overall · higher is betterClaude Haiku 5.5: 21.5%GPT-6.1 Terra: 48.5%Artificial AnalysisAs of 10/29/2026
EMB v1.1Dataroom · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 85.8%GPT-6.1 Terra: 86.3%Vals AIAs of 10/26/2026
Finance Agent v2.1All-Pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 51.8%GPT-6.1 Terra: 42.6%Vals AIAs of 10/26/2026
FrontierCodeOverall · higher is betterClaude Haiku 5.5: 8.0%GPT-6.1 Terra: 24.5%Artificial AnalysisAs of 10/29/2026
FrontierCode 1.1 MainOverall · higher is betterClaude Haiku 5.5: 29.3%GPT-6.1 Terra: 36.3%Artificial AnalysisAs of 10/29/2026
GDP.pdfOverall · higher is betterClaude Haiku 5.5: 11.2%GPT-6.1 Terra: 25.6%Artificial AnalysisAs of 10/29/2026
GDPval-AAOverall · higher is betterClaude Haiku 5.5: 1,130.82 eloGPT-6.1 Terra: 1,204.16 eloArtificial AnalysisAs of 10/29/2026
HLAB-Vals-1.1Antitrust Competition · Task fully resolved · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 0%GPT-6.1 Terra: 0%Vals AIAs of 10/26/2026
Compare another matchup
More matchups
Related LLM comparisons
Compare Claude Haiku 5.5 and GPT-6.1 Terra with other leading models.