BENCHMARK

Introducing Landeed Property Intelligence Benchmark

August 2026   ·   5 min read

We benchmarked Terra Black T2 against four frontier models. It ranked first.

100 real Indian title-verification matters. Five AI models.Terra Black T2 scored 0.891 overall and ranked #1 - ahead of every frontier model tested.

0.891macro score
#1of 5 systems
100real matters

LANDEED PROPERTY INTELLIGENCE BENCH  ·  100 REAL INDIAN PROPERTY MATTERS

Title verification isn’t just a reading test.It takes judgment.

A title-verification report must do more than extract facts - it must connect the evidence, interpret its implications, and reach a defensible conclusion. So we benchmarked 100 real Indian matters against one fixed legal rubric, applied consistently across every model.

100real Indian title matters scored
500+real source documents
8legal dimensions graded
~3-4 minper full title report

The leaderboard

Five systems. One benchmark.Terra Black T2 ranked first.

Across 100 title matters, Terra Black T2 scored 0.891, the highest macro score among the five models tested.

#1 OF 5 SYSTEMS 0.891

macro score - mean criterion pass-rate across 100 title matters

Terra Black T2
0.891
Sonnet-5
0.863
Gemini-3.6
0.852
Opus-4.8
0.844
GPT-5.6
0.769
Property Cases passed in full - every scored criterion satisfied 100 cases · strict all-pass
26
Terra Black T2
14
Sonnet-5
9
Opus-4.8
8
Gemini-3.6
1
GPT-5.6

The average scores are close. The all-pass test is less forgiving.

Where Terra leads

Frontier models read well. Terra Black T2 goes further.

The field is strong at extracting facts from property documents. Terra Black T2’s advantage appears where the work requires applying Indian property law and reaching a judgment, while remaining competitive across the rest of the title-verification workflow.

Pass rate across eight legal dimensions · 100 real Indian title property cases.

DimensionTerra Black T2Sonnet-5Gemini-3.6Opus-4.8GPT-5.6
Statutory & tenure0.8880.7570.8460.7710.682
Mortgage & security0.7970.7160.6910.7030.686
Chain of title0.8880.8800.8880.7980.810
Documents scrutinized0.9380.9380.9260.9070.895
Title opinion & recommendations0.8800.7700.9500.7600.320
Encumbrances & liens0.8840.9190.8490.8600.907
Parties0.9240.9310.7680.9200.720
Property identification0.8930.9170.9380.9300.909

Highest score in each dimension shown in bold. Report structure scored 1.000 for all five and is omitted as a non-differentiator.

#1 of all 5 systems
0.888statutory & tenure standing

Freehold, RERA, tenure and conversion, joint-family interests and minors’ shares, interpreting what they mean for the title.

Ahead of the overall leader
0.797mortgage & security opinion

Assessing whether the property can support a valid and enforceable mortgage.

Case by case

The lead isn’t just in the average.It holds case by case.

Across 100 title matters, Terra Black T2 matched or beat each model on a majority of cases and scored higher on average in every head-to-head comparison.

CASE-LEVEL OUTCOMES · 100 TITLE REVIEWSmean delta per case →

Terra vs.GPT-5.6

87%13%
+0.122

Terra vs.Opus-4.8

57%19%24%
+0.048

Terra vs.Gemini-3.6

73%27%
+0.039

Terra vs.Sonnet-5

51%21%28%
+0.029
Terra higherEqual scoreOpponent higher

Speed & quality

The highest score.In just four minutes.

Terra Black T2 generates a complete title-verification report in ~4 minutes in production, while posting the benchmark’s highest score at 0.891. High-quality property intelligence doesn’t have to mean a long wait.

Robustness & scale

Real-world property matters, at real-world scale.

The benchmark used real title-verification matters spanning large, complex document sets.On one of the benchmark’s hardest matters, Terra Black T2 scored 0.833, the highest of the systems tested.

Case size across the benchmarkmegabytes
9 MBmedian 110 MBlargest 129 MBhardest

File size is shown as a description of the workload, not as a measure of legal difficulty.

The single hardest case (~129 MB)score, higher is better
Terra
0.833
Opus-4.8
0.722
Gemini
0.667
GPT-5.6
0.556

On the single hardest case (~129 MB), Terra produced the highest score of the five systems tested. On the largest case by file size (~110 MB), a frontier model led and Terra trailed at 0.733.

Methodology & disclosure

One benchmark.Five harnesses. Same standard.

One benchmark.Five harnesses. Same standard.

All five models were evaluated on the same 100 title matters, against the same fixed legal rubric, using the same criterion-level scoring process.

ONE FIXED RUBRIC

Every title matter was scored criterion by criterion against the same legal rubric.

CRITERION-LEVEL SCORING

Each requirement was scored independently, then aggregated into matter-, dimension- and benchmark-level scores.

SEPARATE EVALUATOR MODEL

A separate model evaluated every output against the same rubric at temperature 0.

ONE OUTPUT PER TITLE MATTER

One evaluated output per system, per title matter. No best-of-N selection.

Internal benchmark

See what Terra does with your Property Case.

We benchmarked Terra Black T2 on 100 real title-verification matters. Now try it on one your team knows well and compare the evidence it finds, the analysis it produces, and the opinion it reaches.

Test Terra on a property case →