FinSearchComp

Financial data-search benchmark evaluating model+search-tool agents on time-sensitive, simple historical, and complex historical data retrieval for global and Greater China markets.

24rows
avg_accuracyprimary metric
2026-05-28sampled

Metadata

Metrics

Average Accuracy, Time-Sensitive Accuracy, Simple Historical Accuracy, Complex Historical Accuracy

Latest Results

Rows are imported from the official FinSearchComp static homepage tables. Each result is region-specific because Global and Greater China tables are published separately.

Rank Subject Average Accuracy Model Match Provenance Sampled
1 Grok 4 (web) (Global Data Performance) 68.9% average accuracy Imported 2026-05-28
2 GPT-5-Thinking (web) (Global Data Performance) 63.9% average accuracy Imported 2026-05-28
3 Gemini 2.5 pro (web) (Global Data Performance) 42.6% average accuracy Imported 2026-05-28
4 DouBao (web) (Global Data Performance) 39.1% average accuracy Imported 2026-05-28
5 Qwen3-235B-A22B-2507 (web) (Global Data Performance) 37.4% average accuracy Imported 2026-05-28
6 YuanBao (DeepSeek V3) (web) (Global Data Performance) 30.5% average accuracy Imported 2026-05-28
7 YuanBao (HunYuan-T1-Thinking) (web) (Global Data Performance) 29.8% average accuracy Imported 2026-05-28
7 YuanBao (DeepSeek R1) (web) (Global Data Performance) 29.8% average accuracy Imported 2026-05-28
7 DouBao-Thinking (web) (Global Data Performance) 29.8% average accuracy Imported 2026-05-28
10 Kimi k2 (web) (Global Data Performance) 29.5% average accuracy Imported 2026-05-28
11 DeepSeek R1 (web) (Global Data Performance) 17.2% average accuracy Imported 2026-05-28
12 ERNIE X1 (web) (Global Data Performance) 16.6% average accuracy Imported 2026-05-28
1 DouBao (web) (Greater China Data Performance) 54.2% average accuracy Imported 2026-05-28
2 YuanBao (DeepSeek R1) (web) (Greater China Data Performance) 52.5% average accuracy Imported 2026-05-28
3 Grok 4 (web) (Greater China Data Performance) 51.9% average accuracy Imported 2026-05-28
4 YuanBao (HunYuan-T1-Thinking) (web) (Greater China Data Performance) 50.5% average accuracy Imported 2026-05-28
5 DouBao-Thinking (web) (Greater China Data Performance) 49.0% average accuracy Imported 2026-05-28
6 YuanBao (DeepSeek V3) (web) (Greater China Data Performance) 48.8% average accuracy Imported 2026-05-28
7 GPT-5-Thinking (web) (Greater China Data Performance) 46.4% average accuracy Imported 2026-05-28
8 ERNIE X1 (web) (Greater China Data Performance) 40.8% average accuracy Imported 2026-05-28
9 DeepSeek R1 (web) (Greater China Data Performance) 40.5% average accuracy Imported 2026-05-28
10 Kimi k2 (web) (Greater China Data Performance) 38.3% average accuracy Imported 2026-05-28
11 Gemini 2.5 pro (web) (Greater China Data Performance) 36.8% average accuracy Imported 2026-05-28
12 Qwen3-235B-A22B-2507 (web) (Greater China Data Performance) 21.9% average accuracy Imported 2026-05-28