text_classification_table.html

<link rel="stylesheet" href="static/css/tooltips.css">
<style>
.tooltip-right:hover::after {
  left: auto \!important;
  right: 100% \!important;
  margin-left: 0 \!important;
  margin-right: 10px \!important;
}
</style>
<!-- Text Classification -->
<div id="text-classification" class="tab-content">
  <h2 class="title is-4">Text Classification Task Results</h2>
  <div class="results-table">
    <table class="table is-bordered is-striped is-narrow is-hoverable is-fullwidth">
      <thead>
        <tr>
          <th rowspan="2">Model</th>
          <th colspan="4" class="has-text-centered tooltip-trigger" data-title="Banking77" data-tooltip="Banking77 is a fine-grained dataset comprising 13,083 customer service queries annotated with 77 unique intents from the banking domain. The task involves accurately classifying each customer query into the correct intent category to improve automated banking support systems.">Banking77</th>
          <th colspan="4" class="has-text-centered tooltip-trigger" data-title="FinBench" data-tooltip="FinBench is a comprehensive evaluation dataset containing 333,000 labeled instances that combines tabular data and profile text for financial risk prediction. The task requires models to predict financial outcomes across three key risk categories: default, fraud, and customer churn.">FinBench</th>
          <th colspan="4" class="has-text-centered tooltip-trigger" data-title="FOMC" data-tooltip="FOMC is a dataset containing Federal Open Market Committee speeches, meeting minutes, and press conference transcripts spanning from 1996 to 2022. The classification task involves determining whether the monetary policy stance expressed in each document is hawkish (tighter monetary policy) or dovish (looser monetary policy).">FOMC</th>
          <th colspan="4" class="has-text-centered tooltip-trigger tooltip-right" style="position: relative;" data-title="NumClaim" data-tooltip="NumClaim is an expert-annotated dataset for detecting and analyzing fine-grained investor claims within financial narratives that contain numerical information. The task requires identifying and categorizing claims containing numerals in analyst reports and earnings call transcripts for investment decision making.">NumClaim</th>
          <th colspan="1" class="has-text-centered tooltip-trigger tooltip-right" data-title="Headlines" data-tooltip="Headlines is a dataset containing 11,412 human-annotated financial news headlines focused on commodities, particularly gold, spanning from 2000 to 2019. The classification task involves identifying binary indicators for price mentions and directional price movements in these concise financial texts.">Headlines</th>
        </tr>
        <tr>
          <th class="has-text-centered">Accuracy</th>
          <th class="has-text-centered">Precision</th>
          <th class="has-text-centered">Recall</th>
          <th class="has-text-centered">F1</th>
          <th class="has-text-centered">Accuracy</th>
          <th class="has-text-centered">Precision</th>
          <th class="has-text-centered">Recall</th>
          <th class="has-text-centered">F1</th>
          <th class="has-text-centered">Accuracy</th>
          <th class="has-text-centered">Precision</th>
          <th class="has-text-centered">Recall</th>
          <th class="has-text-centered">F1</th>
          <th class="has-text-centered">Accuracy</th>
          <th class="has-text-centered">Precision</th>
          <th class="has-text-centered">Recall</th>
          <th class="has-text-centered">F1</th>
          <th class="has-text-centered">Accuracy</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <td class="tooltip-trigger" data-title="Llama 3 70B Instruct" data-tooltip="Meta's advanced 70 billion parameter dense language model optimized for instruction-following tasks. Available through Together AI and notable for complex reasoning capabilities.">Llama 3 70B Instruct</td>
          <td class="has-text-centered">0.660</td>
          <td class="has-text-centered">0.748</td>
          <td class="has-text-centered">0.660</td>
          <td class="has-text-centered">0.645</td>
          <td class="has-text-centered">0.222</td>
          <td class="has-text-centered">0.826</td>
          <td class="has-text-centered">0.222</td>
          <td class="has-text-centered">0.309</td>
          <td class="has-text-centered">0.661</td>
          <td class="has-text-centered">0.662</td>
          <td class="has-text-centered">0.661</td>
          <td class="has-text-centered">0.652</td>
          <td class="has-text-centered">0.430</td>
          <td class="has-text-centered">0.240</td>
          <td class="has-text-centered performance-medium">0.980</td>
          <td class="has-text-centered">0.386</td>
          <td class="has-text-centered">0.811</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Llama 3 8B Instruct" data-tooltip="Meta's efficient 8 billion parameter language model optimized for instruction-following. Balances performance and efficiency for financial tasks with reasonable reasoning capabilities.">Llama 3 8B Instruct</td>
          <td class="has-text-centered">0.534</td>
          <td class="has-text-centered">0.672</td>
          <td class="has-text-centered">0.534</td>
          <td class="has-text-centered">0.512</td>
          <td class="has-text-centered">0.543</td>
          <td class="has-text-centered">0.857</td>
          <td class="has-text-centered">0.543</td>
          <td class="has-text-centered">0.659</td>
          <td class="has-text-centered">0.565</td>
          <td class="has-text-centered">0.618</td>
          <td class="has-text-centered">0.565</td>
          <td class="has-text-centered">0.497</td>
          <td class="has-text-centered">0.801</td>
          <td class="has-text-centered">0.463</td>
          <td class="has-text-centered">0.571</td>
          <td class="has-text-centered">0.511</td>
          <td class="has-text-centered">0.763</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="DBRX Instruct" data-tooltip="Databricks' 132 billion parameter Mixture of Experts (MoE) model focused on advanced reasoning. Demonstrates competitive performance on financial tasks with strong text processing capabilities.">DBRX Instruct</td>
          <td class="has-text-centered">0.578</td>
          <td class="has-text-centered">0.706</td>
          <td class="has-text-centered">0.578</td>
          <td class="has-text-centered">0.574</td>
          <td class="has-text-centered">0.359</td>
          <td class="has-text-centered">0.851</td>
          <td class="has-text-centered">0.359</td>
          <td class="has-text-centered">0.483</td>
          <td class="has-text-centered">0.285</td>
          <td class="has-text-centered">0.572</td>
          <td class="has-text-centered">0.285</td>
          <td class="has-text-centered">0.193</td>
          <td class="has-text-centered">0.222</td>
          <td class="has-text-centered">0.190</td>
          <td class="has-text-centered performance-best">1.000</td>
          <td class="has-text-centered">0.319</td>
          <td class="has-text-centered">0.746</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="DeepSeek LLM (67B)" data-tooltip="DeepSeek's 67 billion parameter model optimized for chat applications. Balances performance and efficiency across financial tasks with solid reasoning capabilities.">DeepSeek LLM (67B)</td>
          <td class="has-text-centered">0.596</td>
          <td class="has-text-centered">0.711</td>
          <td class="has-text-centered">0.596</td>
          <td class="has-text-centered">0.578</td>
          <td class="has-text-centered">0.369</td>
          <td class="has-text-centered">0.856</td>
          <td class="has-text-centered">0.369</td>
          <td class="has-text-centered">0.492</td>
          <td class="has-text-centered">0.532</td>
          <td class="has-text-centered">0.678</td>
          <td class="has-text-centered">0.532</td>
          <td class="has-text-centered">0.407</td>
          <td class="has-text-centered">0.832</td>
          <td class="has-text-centered performance-best">1.000</td>
          <td class="has-text-centered">0.082</td>
          <td class="has-text-centered">0.151</td>
          <td class="has-text-centered">0.778</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Gemma 2 27B" data-tooltip="Google's open-weight 27 billion parameter model optimized for reasoning tasks. Balances performance and efficiency across financial domains with strong instruction-following.">Gemma 2 27B</td>
          <td class="has-text-centered">0.639</td>
          <td class="has-text-centered">0.730</td>
          <td class="has-text-centered">0.639</td>
          <td class="has-text-centered">0.621</td>
          <td class="has-text-centered">0.410</td>
          <td class="has-text-centered">0.849</td>
          <td class="has-text-centered">0.410</td>
          <td class="has-text-centered">0.538</td>
          <td class="has-text-centered">0.651</td>
          <td class="has-text-centered">0.704</td>
          <td class="has-text-centered">0.651</td>
          <td class="has-text-centered">0.620</td>
          <td class="has-text-centered">0.471</td>
          <td class="has-text-centered">0.257</td>
          <td class="has-text-centered performance-best">1.000</td>
          <td class="has-text-centered">0.408</td>
          <td class="has-text-centered">0.808</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Gemma 2 9B" data-tooltip="Google's efficient open-weight 9 billion parameter model. Demonstrates good performance on financial tasks relative to its smaller size.">Gemma 2 9B</td>
          <td class="has-text-centered">0.630</td>
          <td class="has-text-centered">0.710</td>
          <td class="has-text-centered">0.630</td>
          <td class="has-text-centered">0.609</td>
          <td class="has-text-centered">0.412</td>
          <td class="has-text-centered">0.848</td>
          <td class="has-text-centered">0.412</td>
          <td class="has-text-centered">0.541</td>
          <td class="has-text-centered">0.595</td>
          <td class="has-text-centered">0.694</td>
          <td class="has-text-centered">0.595</td>
          <td class="has-text-centered">0.519</td>
          <td class="has-text-centered">0.371</td>
          <td class="has-text-centered">0.224</td>
          <td class="has-text-centered performance-strong">0.990</td>
          <td class="has-text-centered">0.365</td>
          <td class="has-text-centered performance-best">0.856</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Mistral (7B) Instruct v0.3" data-tooltip="Mistral AI's 7 billion parameter instruction-tuned model. Demonstrates impressive efficiency with reasonable performance on financial tasks despite its smaller size.">Mistral (7B) Instruct v0.3</td>
          <td class="has-text-centered">0.547</td>
          <td class="has-text-centered">0.677</td>
          <td class="has-text-centered">0.547</td>
          <td class="has-text-centered">0.528</td>
          <td class="has-text-centered">0.375</td>
          <td class="has-text-centered">0.839</td>
          <td class="has-text-centered">0.375</td>
          <td class="has-text-centered">0.503</td>
          <td class="has-text-centered">0.587</td>
          <td class="has-text-centered">0.598</td>
          <td class="has-text-centered">0.587</td>
          <td class="has-text-centered">0.542</td>
          <td class="has-text-centered">0.521</td>
          <td class="has-text-centered">0.266</td>
          <td class="has-text-centered">0.918</td>
          <td class="has-text-centered">0.412</td>
          <td class="has-text-centered">0.779</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Mixtral-8x22B Instruct" data-tooltip="Mistral AI's 141 billion parameter MoE model with eight 22B expert networks. Features robust reasoning capabilities for financial tasks with strong instruction-following performance.">Mixtral-8x22B Instruct</td>
          <td class="has-text-centered">0.622</td>
          <td class="has-text-centered">0.718</td>
          <td class="has-text-centered">0.622</td>
          <td class="has-text-centered">0.602</td>
          <td class="has-text-centered">0.166</td>
          <td class="has-text-centered">0.811</td>
          <td class="has-text-centered">0.166</td>
          <td class="has-text-centered">0.221</td>
          <td class="has-text-centered">0.562</td>
          <td class="has-text-centered">0.709</td>
          <td class="has-text-centered">0.562</td>
          <td class="has-text-centered">0.465</td>
          <td class="has-text-centered">0.732</td>
          <td class="has-text-centered">0.384</td>
          <td class="has-text-centered">0.775</td>
          <td class="has-text-centered">0.513</td>
          <td class="has-text-centered performance-medium">0.835</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Mixtral-8x7B Instruct" data-tooltip="Mistral AI's 47 billion parameter MoE model with eight 7B expert networks. Balances efficiency and performance with reasonable financial reasoning capabilities.">Mixtral-8x7B Instruct</td>
          <td class="has-text-centered">0.567</td>
          <td class="has-text-centered">0.693</td>
          <td class="has-text-centered">0.567</td>
          <td class="has-text-centered">0.547</td>
          <td class="has-text-centered">0.285</td>
          <td class="has-text-centered">0.838</td>
          <td class="has-text-centered">0.285</td>
          <td class="has-text-centered">0.396</td>
          <td class="has-text-centered">0.623</td>
          <td class="has-text-centered">0.636</td>
          <td class="has-text-centered">0.623</td>
          <td class="has-text-centered">0.603</td>
          <td class="has-text-centered">0.765</td>
          <td class="has-text-centered">0.431</td>
          <td class="has-text-centered">0.898</td>
          <td class="has-text-centered">0.583</td>
          <td class="has-text-centered">0.805</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Qwen 2 Instruct (72B)" data-tooltip="Alibaba's 72 billion parameter instruction-following model optimized for reasoning tasks. Features strong performance on financial domains with advanced text processing capabilities.">Qwen 2 Instruct (72B)</td>
          <td class="has-text-centered">0.644</td>
          <td class="has-text-centered">0.730</td>
          <td class="has-text-centered">0.644</td>
          <td class="has-text-centered">0.627</td>
          <td class="has-text-centered">0.370</td>
          <td class="has-text-centered">0.848</td>
          <td class="has-text-centered">0.370</td>
          <td class="has-text-centered">0.495</td>
          <td class="has-text-centered">0.623</td>
          <td class="has-text-centered">0.639</td>
          <td class="has-text-centered">0.623</td>
          <td class="has-text-centered">0.605</td>
          <td class="has-text-centered">0.821</td>
          <td class="has-text-centered">0.506</td>
          <td class="has-text-centered">0.867</td>
          <td class="has-text-centered">0.639</td>
          <td class="has-text-centered">0.830</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="WizardLM-2 8x22B" data-tooltip="A 176 billion parameter MoE model focused on complex reasoning. Designed for advanced instruction-following with strong capabilities across financial tasks.">WizardLM-2 8x22B</td>
          <td class="has-text-centered">0.664</td>
          <td class="has-text-centered">0.737</td>
          <td class="has-text-centered">0.664</td>
          <td class="has-text-centered">0.648</td>
          <td class="has-text-centered">0.373</td>
          <td class="has-text-centered">0.842</td>
          <td class="has-text-centered">0.373</td>
          <td class="has-text-centered">0.500</td>
          <td class="has-text-centered">0.583</td>
          <td class="has-text-centered performance-medium">0.710</td>
          <td class="has-text-centered">0.583</td>
          <td class="has-text-centered">0.505</td>
          <td class="has-text-centered">0.831</td>
          <td class="has-text-centered">0.630</td>
          <td class="has-text-centered">0.173</td>
          <td class="has-text-centered">0.272</td>
          <td class="has-text-centered">0.797</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="DeepSeek-V3" data-tooltip="DeepSeek's 685 billion parameter Mixture of Experts (MoE) model optimized for advanced reasoning. Strong performance on financial tasks with robust instruction-following capabilities.">DeepSeek-V3</td>
          <td class="has-text-centered performance-strong">0.722</td>
          <td class="has-text-centered performance-medium">0.774</td>
          <td class="has-text-centered performance-strong">0.722</td>
          <td class="has-text-centered performance-strong">0.714</td>
          <td class="has-text-centered">0.362</td>
          <td class="has-text-centered">0.845</td>
          <td class="has-text-centered">0.362</td>
          <td class="has-text-centered">0.487</td>
          <td class="has-text-centered">0.625</td>
          <td class="has-text-centered performance-strong">0.712</td>
          <td class="has-text-centered">0.625</td>
          <td class="has-text-centered">0.578</td>
          <td class="has-text-centered">0.860</td>
          <td class="has-text-centered">0.586</td>
          <td class="has-text-centered">0.796</td>
          <td class="has-text-centered">0.675</td>
          <td class="has-text-centered">0.729</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="DeepSeek R1" data-tooltip="DeepSeek's premium 671 billion parameter Mixture of Experts (MoE) model representing their most advanced offering. Designed for state-of-the-art performance across complex reasoning and financial tasks.">DeepSeek R1</td>
          <td class="has-text-centered performance-best">0.772</td>
          <td class="has-text-centered performance-strong">0.789</td>
          <td class="has-text-centered performance-best">0.772</td>
          <td class="has-text-centered performance-best">0.763</td>
          <td class="has-text-centered">0.306</td>
          <td class="has-text-centered">0.846</td>
          <td class="has-text-centered">0.306</td>
          <td class="has-text-centered">0.419</td>
          <td class="has-text-centered performance-strong">0.679</td>
          <td class="has-text-centered">0.682</td>
          <td class="has-text-centered performance-strong">0.679</td>
          <td class="has-text-centered performance-strong">0.670</td>
          <td class="has-text-centered">0.851</td>
          <td class="has-text-centered">0.557</td>
          <td class="has-text-centered">0.898</td>
          <td class="has-text-centered">0.688</td>
          <td class="has-text-centered">0.769</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="QwQ-32B-Preview" data-tooltip="Qwen's experimental 32 billion parameter MoE model focused on efficient computation. Features interesting performance characteristics on certain financial tasks.">QwQ-32B-Preview</td>
          <td class="has-text-centered">0.577</td>
          <td class="has-text-centered">0.747</td>
          <td class="has-text-centered">0.577</td>
          <td class="has-text-centered">0.613</td>
          <td class="has-text-centered performance-strong">0.716</td>
          <td class="has-text-centered performance-strong">0.871</td>
          <td class="has-text-centered performance-strong">0.716</td>
          <td class="has-text-centered performance-strong">0.784</td>
          <td class="has-text-centered">0.591</td>
          <td class="has-text-centered">0.630</td>
          <td class="has-text-centered">0.591</td>
          <td class="has-text-centered">0.555</td>
          <td class="has-text-centered">0.819</td>
          <td class="has-text-centered performance-best">1.000</td>
          <td class="has-text-centered">0.010</td>
          <td class="has-text-centered">0.020</td>
          <td class="has-text-centered">0.744</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Jamba 1.5 Mini" data-tooltip="A compact variant in the Jamba model series focused on efficiency. Balances performance and computational requirements for financial tasks.">Jamba 1.5 Mini</td>
          <td class="has-text-centered">0.528</td>
          <td class="has-text-centered">0.630</td>
          <td class="has-text-centered">0.528</td>
          <td class="has-text-centered">0.508</td>
          <td class="has-text-centered performance-best">0.913</td>
          <td class="has-text-centered performance-best">0.883</td>
          <td class="has-text-centered performance-best">0.913</td>
          <td class="has-text-centered performance-best">0.898</td>
          <td class="has-text-centered">0.572</td>
          <td class="has-text-centered">0.678</td>
          <td class="has-text-centered">0.572</td>
          <td class="has-text-centered">0.499</td>
          <td class="has-text-centered">0.812</td>
          <td class="has-text-centered">0.429</td>
          <td class="has-text-centered">0.092</td>
          <td class="has-text-centered">0.151</td>
          <td class="has-text-centered">0.682</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Jamba 1.5 Large" data-tooltip="An expanded variant in the Jamba model series with enhanced capabilities. Features stronger reasoning for financial tasks than its smaller counterpart.">Jamba 1.5 Large</td>
          <td class="has-text-centered">0.642</td>
          <td class="has-text-centered">0.746</td>
          <td class="has-text-centered">0.642</td>
          <td class="has-text-centered">0.628</td>
          <td class="has-text-centered">0.494</td>
          <td class="has-text-centered">0.851</td>
          <td class="has-text-centered">0.494</td>
          <td class="has-text-centered">0.618</td>
          <td class="has-text-centered">0.597</td>
          <td class="has-text-centered">0.650</td>
          <td class="has-text-centered">0.597</td>
          <td class="has-text-centered">0.550</td>
          <td class="has-text-centered">0.855</td>
          <td class="has-text-centered">0.639</td>
          <td class="has-text-centered">0.469</td>
          <td class="has-text-centered">0.541</td>
          <td class="has-text-centered">0.782</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Claude 3.5 Sonnet" data-tooltip="Anthropic's advanced proprietary language model optimized for complex reasoning and instruction-following. Features enhanced performance on financial tasks with strong text processing capabilities.">Claude 3.5 Sonnet</td>
          <td class="has-text-centered">0.682</td>
          <td class="has-text-centered">0.755</td>
          <td class="has-text-centered">0.682</td>
          <td class="has-text-centered">0.668</td>
          <td class="has-text-centered">0.513</td>
          <td class="has-text-centered">0.854</td>
          <td class="has-text-centered">0.513</td>
          <td class="has-text-centered">0.634</td>
          <td class="has-text-centered performance-medium">0.675</td>
          <td class="has-text-centered">0.677</td>
          <td class="has-text-centered performance-medium">0.675</td>
          <td class="has-text-centered performance-best">0.674</td>
          <td class="has-text-centered performance-medium">0.879</td>
          <td class="has-text-centered">0.646</td>
          <td class="has-text-centered">0.745</td>
          <td class="has-text-centered performance-medium">0.692</td>
          <td class="has-text-centered">0.827</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Claude 3 Haiku" data-tooltip="Anthropic's smaller efficiency-focused model in the Claude family. Designed for speed and lower computational requirements while maintaining reasonable performance on financial tasks.">Claude 3 Haiku</td>
          <td class="has-text-centered">0.639</td>
          <td class="has-text-centered">0.735</td>
          <td class="has-text-centered">0.639</td>
          <td class="has-text-centered">0.622</td>
          <td class="has-text-centered">0.067</td>
          <td class="has-text-centered">0.674</td>
          <td class="has-text-centered">0.067</td>
          <td class="has-text-centered">0.022</td>
          <td class="has-text-centered">0.633</td>
          <td class="has-text-centered">0.634</td>
          <td class="has-text-centered">0.633</td>
          <td class="has-text-centered">0.631</td>
          <td class="has-text-centered">0.838</td>
          <td class="has-text-centered">0.556</td>
          <td class="has-text-centered">0.561</td>
          <td class="has-text-centered">0.558</td>
          <td class="has-text-centered">0.781</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Cohere Command R 7B" data-tooltip="Cohere's 7-billion parameter model focused on instruction-following. An efficient model with reasonable financial domain capabilities for its size.">Cohere Command R 7B</td>
          <td class="has-text-centered">0.530</td>
          <td class="has-text-centered">0.650</td>
          <td class="has-text-centered">0.530</td>
          <td class="has-text-centered">0.516</td>
          <td class="has-text-centered performance-medium">0.682</td>
          <td class="has-text-centered performance-medium">0.868</td>
          <td class="has-text-centered performance-medium">0.682</td>
          <td class="has-text-centered performance-medium">0.762</td>
          <td class="has-text-centered">0.536</td>
          <td class="has-text-centered">0.505</td>
          <td class="has-text-centered">0.536</td>
          <td class="has-text-centered">0.459</td>
          <td class="has-text-centered">0.797</td>
          <td class="has-text-centered">0.210</td>
          <td class="has-text-centered">0.041</td>
          <td class="has-text-centered">0.068</td>
          <td class="has-text-centered">0.770</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Cohere Command R +" data-tooltip="Cohere's enhanced command model with improved instruction-following capabilities. Features advanced reasoning for financial domains with stronger performance than its smaller counterpart.">Cohere Command R +</td>
          <td class="has-text-centered">0.660</td>
          <td class="has-text-centered">0.747</td>
          <td class="has-text-centered">0.660</td>
          <td class="has-text-centered">0.651</td>
          <td class="has-text-centered">0.575</td>
          <td class="has-text-centered">0.859</td>
          <td class="has-text-centered">0.575</td>
          <td class="has-text-centered">0.684</td>
          <td class="has-text-centered">0.526</td>
          <td class="has-text-centered">0.655</td>
          <td class="has-text-centered">0.526</td>
          <td class="has-text-centered">0.393</td>
          <td class="has-text-centered">0.804</td>
          <td class="has-text-centered">0.333</td>
          <td class="has-text-centered">0.071</td>
          <td class="has-text-centered">0.118</td>
          <td class="has-text-centered">0.812</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="Google Gemini 1.5 Pro" data-tooltip="Google's advanced proprietary multimodal model designed for complex reasoning and instruction-following tasks. Features strong performance across financial domains with advanced reasoning capabilities.">Google Gemini 1.5 Pro</td>
          <td class="has-text-centered">0.483</td>
          <td class="has-text-centered">0.487</td>
          <td class="has-text-centered">0.483</td>
          <td class="has-text-centered">0.418</td>
          <td class="has-text-centered">0.240</td>
          <td class="has-text-centered">0.823</td>
          <td class="has-text-centered">0.240</td>
          <td class="has-text-centered">0.336</td>
          <td class="has-text-centered">0.619</td>
          <td class="has-text-centered">0.667</td>
          <td class="has-text-centered">0.619</td>
          <td class="has-text-centered">0.579</td>
          <td class="has-text-centered">0.700</td>
          <td class="has-text-centered">0.369</td>
          <td class="has-text-centered">0.908</td>
          <td class="has-text-centered">0.525</td>
          <td class="has-text-centered performance-strong">0.837</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="OpenAI gpt-4o" data-tooltip="OpenAI's flagship multimodal model optimized for a balance of quality and speed. Features strong performance across diverse tasks with capabilities for complex financial reasoning and instruction following.">OpenAI gpt-4o</td>
          <td class="has-text-centered performance-medium">0.704</td>
          <td class="has-text-centered performance-best">0.792</td>
          <td class="has-text-centered performance-medium">0.704</td>
          <td class="has-text-centered performance-medium">0.710</td>
          <td class="has-text-centered">0.396</td>
          <td class="has-text-centered">0.846</td>
          <td class="has-text-centered">0.396</td>
          <td class="has-text-centered">0.524</td>
          <td class="has-text-centered performance-best">0.681</td>
          <td class="has-text-centered performance-best">0.719</td>
          <td class="has-text-centered performance-best">0.681</td>
          <td class="has-text-centered performance-medium">0.664</td>
          <td class="has-text-centered performance-best">0.896</td>
          <td class="has-text-centered performance-medium">0.667</td>
          <td class="has-text-centered">0.857</td>
          <td class="has-text-centered performance-best">0.750</td>
          <td class="has-text-centered">0.824</td>
        </tr>
        <tr>
          <td class="tooltip-trigger" data-title="OpenAI o1-mini" data-tooltip="OpenAI's smaller advanced model balancing efficiency and performance. Demonstrates surprisingly strong results on financial tasks despite its reduced parameter count.">OpenAI o1-mini</td>
          <td class="has-text-centered">0.681</td>
          <td class="has-text-centered">0.760</td>
          <td class="has-text-centered">0.681</td>
          <td class="has-text-centered">0.670</td>
          <td class="has-text-centered">0.487</td>
          <td class="has-text-centered">0.851</td>
          <td class="has-text-centered">0.487</td>
          <td class="has-text-centered">0.612</td>
          <td class="has-text-centered">0.651</td>
          <td class="has-text-centered">0.670</td>
          <td class="has-text-centered">0.651</td>
          <td class="has-text-centered">0.635</td>
          <td class="has-text-centered performance-strong">0.888</td>
          <td class="has-text-centered performance-medium">0.664</td>
          <td class="has-text-centered">0.786</td>
          <td class="has-text-centered performance-strong">0.720</td>
          <td class="has-text-centered">0.769</td>
        </tr>
      </tbody>
    </table>
    <div class="content is-small mt-4">
      <p><strong>Note:</strong> Color highlighting indicates performance ranking: 
        <span class="performance-best">&nbsp;Best&nbsp;</span>, 
        <span class="performance-medium">&nbsp;Strong&nbsp;</span>,
        <span class="performance-low">&nbsp;Good&nbsp;</span>
      </p>
    </div>
  </div>
</div><script src="static/js/tooltips.js"></script>
<script src="static/js/fixed-tooltips.js"></script>