---
title: "ConvFinQA - Benchmark Evaluation - FinanceBenchmark"
description: "Multi-turn conversational financial reasoning over earnings documents."
canonical: "https://financebenchmark.ai/benchmarks/convfinqa"
type: "text/markdown"
---
# ConvFinQA

> Multi-turn conversational financial reasoning over earnings documents.

## Table of Contents
- [1. Specifications & Metadata](#specifications)
- [2. Model Rankings on this Benchmark](#rankings)
- [3. Source Attribution & Citation](#attribution)

## 1. Specifications & Metadata {#specifications}

- **Slug:** `convfinqa`
- **Domain Categories:** documentQA
- **Composite Weight:** 20 (Tier 2)
- **Task Count:** 3,892 tasks
- **Source / Publisher:** arXiv:2210.03849
- **Research Paper:** [https://arxiv.org/abs/2210.03849](https://arxiv.org/abs/2210.03849)
- **arXiv ID:** [arXiv:2210.03849](https://arxiv.org/abs/2210.03849)

## 2. Model Rankings on this Benchmark {#rankings}

| Rank | Model | Organization | Overall | Eval Date | Source |
|:----:|:------|:-------------|:---:|:---------:|:------:|
| 1 | [GPT-5.5](https://financebenchmark.ai/models/gpt-5-5.md) | OpenAI | **88.0** | 2026-04 | [Ref](https://arxiv.org/abs/2210.03849) |
| 2 | [Claude Opus 4.7](https://financebenchmark.ai/models/claude-opus-4-7.md) | Anthropic | **86.0** | 2026-03 | [Ref](https://arxiv.org/abs/2210.03849) |
| 3 | [DeepSeek V4 Pro](https://financebenchmark.ai/models/deepseek-v4-pro.md) | DeepSeek | **83.0** | 2026-03 | [Ref](https://arxiv.org/abs/2210.03849) |
| 4 | [Gemini 3.1 Pro](https://financebenchmark.ai/models/gemini-3-1-pro.md) | Google | **82.0** | 2026-03 | [Ref](https://arxiv.org/abs/2210.03849) |
| 5 | [Grok 4.3](https://financebenchmark.ai/models/grok-4-3.md) | xAI | **79.0** | 2026-04 | [Ref](https://arxiv.org/abs/2210.03849) |
| 6 | [Kimi K2.6](https://financebenchmark.ai/models/kimi-k2-6.md) | Moonshot AI | **78.0** | 2026-04 | [Ref](https://arxiv.org/abs/2210.03849) |
| 7 | [GLM-5.1](https://financebenchmark.ai/models/glm-5-1.md) | Zhipu AI | **75.0** | 2026-03 | [Ref](https://arxiv.org/abs/2210.03849) |
| 8 | [MiniMax M2.7](https://financebenchmark.ai/models/minimax-m2-7.md) | MiniMax | **73.0** | 2026-03 | [Ref](https://arxiv.org/abs/2210.03849) |

## 3. Source Attribution & Citation {#attribution}

All scores for ConvFinQA are derived directly from published literature or reproducible evaluation harnesses.
To submit updated evaluations, email [submit@financebenchmark.ai](mailto:submit@financebenchmark.ai).