reasoning benchmark
FinSearchComp-T3
FinSearchComp-T3 is a benchmark for evaluating financial search and reasoning capabilities, testing models' ability to retrieve and analyze financial information using tools.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
FinSearchComp-T3 Ranking
Higher score ranks better on this benchmark.
| 01 | MA | 47.4% | 100.0% | 1 | C |
FinSearchComp-T3 Highlights
The leading models and scores on this benchmark.
What is FinSearchComp-T3?
What FinSearchComp-T3 measures and how its scores work.
FinSearchComp-T3 is a benchmark for evaluating financial search and reasoning capabilities, testing models' ability to retrieve and analyze financial information using tools.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- FinSearchComp-T3
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- finsearchcomp-t3|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about FinSearchComp-T3.
Which model scores highest on FinSearchComp-T3?
Kimi K2-Thinking-0905 is currently ranked first with 47.4%.
What does FinSearchComp-T3 measure?
FinSearchComp-T3 is a benchmark for evaluating financial search and reasoning capabilities, testing models' ability to retrieve and analyze financial information using tools.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.