Benchmark
finsearchcomp-greater-china
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages.
All agentic benchmarksScores from FinSearchComp docs.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 0.56
Score distribution
- 39.3%
- Mean
- 40.5%
- Median
- 9.3%
- Std dev
- 36.8%
- 10th percentile
- 51.9%
- 90th percentile
- 21.9%
- Min
This benchmark has a weight of 0.56 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Grok 4· FinSearchComp docs | 51.9% |
| 2 | GPT 5thinking· FinSearchComp docs | 46.4% |
| 3 | DeepSeek R1· FinSearchComp docs | 40.5% |
| 4 | Kimi K2· FinSearchComp docs | 38.3% |
| 5 | Gemini 2.5 Pro· FinSearchComp docs | 36.8% |
| 6 | Qwen3 235B A22B Instruct 2507· FinSearchComp docs | 21.9% |
Data credits: FinSearchComp, CC BY 4.0 (licence)