Public evaluations
Headline results are useful only when the evaluated questions, exact comparators, supporting evidence, and limitations remain attached. This page is the canonical index for SPARKIT's published benchmark claims.
Measured June 2026 · Results updated July 15, 2026
Accuracy
149 questions · biology / medicine + chemistry
SPARKIT answered 54.4% of the 149 evaluated HLE-Gold questions correctly, compared with 39.0% for direct GPT-5.6-Sol and 34.9% for direct Claude Opus 4.8.
Methods, evidence, and limitations →| System | Mode | Accuracy |
|---|---|---|
| SPARKITSPARKIT research-agent run | SPARKIT research-agent run | 54.4% |
| GPT-5.6-SolDirect model call | Direct model call | 39.0% |
| Claude Opus 4.8Direct model call | Direct model call | 34.9% |
Accuracy
127 questions
SPARKIT answered 73.2% of the 127 evaluated GAIA questions correctly, compared with 58.2% for Exa and 57.0% for Brave.
Methods, evidence, and limitations →| System | Mode | Accuracy |
|---|---|---|
| SPARKITSPARKIT research-agent run | SPARKIT research-agent run | 73.2% |
| ExaSearch API result | Search API result | 58.2% |
| BraveSearch API result | Search API result | 57.0% |
SPARKIT