Fin-R1: benchmark results
Provider: Other.
Aggregate Rating 1454 ± 36, rank #3617 of 10916 rated models, from 33 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Fin-RATE | 23.51 | Macro Accuracy (imported) | 75 |
| FinChain | 57.34 | ChainEval (imported) | 75 |
| FinReasoning (Deep Insight) | 73.7 | Rubric score (0-100): a judge score fused from DeepSeek-V3 a | 38.9 |
| FinReasoning (Deep Insight) - Architectural Richness and Strictness | 77.9 | Rubric score (0-100): a judge score fused from DeepSeek-V3 a | 38.9 |
| FinReasoning (Deep Insight) - Completeness and Comparative Analysis | 73.5 | Rubric score (0-100): a judge score fused from DeepSeek-V3 a | 38.9 |
| FinReasoning (Deep Insight) - Factuality and Contextualization | 71.8 | Rubric score (0-100): a judge score fused from DeepSeek-V3 a | 38.9 |
| FinReasoning (Deep Insight) - Justification and Causal Depth | 71.5 | Rubric score (0-100): a judge score fused from DeepSeek-V3 a | 38.9 |
| ShiJianBench | 56.39 | Advisor impact score (0-100): compliance-gated composite 0.7 | 25 |
| ShiJianBench (Bear Market) | 56.94 | Advisor impact score (0-100) recomputed within the bear-mark | 25 |
| ShiJianBench (Bull Market) | 33.11 | Advisor impact score (0-100) recomputed within the bull-mark | 25 |
| ShiJianBench (Range-Bound Market) | 42.69 | Advisor impact score (0-100) recomputed within the range-bou | 25 |
| ShiJianBench - Advisory Content Quality | 51.04 | Content score (0-100): 0.3 x accuracy + 0.7 x personalizatio | 25 |
Interactive version: theaggregate.ai/model?slug=fin-r1 · How It Works · Data refreshed daily, snapshot 2026-11-08.