# Vals CorpFin v2 (CorpFin v2)

> Vals AI private benchmark for understanding long-context credit agreements.

Canonical page: https://benchlm.ai/benchmarks/valscorpfinv2

- Category: [Agentic](/agentic)
- Last updated: August 12, 2026

## About CorpFin v2

- Year: 2026
- Tasks: Credit-agreement understanding tasks
- Format: Accuracy score
- Difficulty: Professional finance document reasoning
- Paper: [CorpFin v2](https://www.vals.ai/benchmarks/corp_fin_v2)

The Vals CorpFin v2 page reports overall, exact-page, max-fitting-context, and shared-max-context task views. BenchLM keeps it display only.

CorpFin v2 is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (134 models)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [Claude Opus 5](/models/claude-opus-5) | — | Anthropic | 73.19% |
| 2 | [Claude Fable 5](/models/claude-fable) | — | Anthropic | 71.83% |
| 3 | [Kimi K3](/models/kimi-k3) | — | Moonshot AI | 71.56% |
| 4 | [Muse Spark 1.1](/models/muse-spark-1-1) | xhigh reasoning | Meta | 71.29% |
| 5 | [Muse Spark 1.2](/models/muse-spark-1-2) | xhigh reasoning | Meta | 70.94% |
| 6 | [Inkling-Small](/models/inkling-small) | 0.99 reasoning | Thinking Machines Lab | 69.62% |
| 7 | [Inkling](/models/inkling) | 0.99 reasoning | Thinking Machines Lab | 68.57% |
| 8 | [Grok 4.3](/models/grok-4-3) | — | xAI | 68.53% |
| 9 | [GPT-5.5](/models/gpt-5-5) | xhigh reasoning | OpenAI | 68.42% |
| 10 | [Kimi K2.5 Thinking](https://www.vals.ai/models/kimi_kimi-k2.5-thinking) | — | Moonshot AI | 68.26% |
| 11 | [MiniMax M3](/models/minimax-m3) | — | MiniMax | 68.10% |
| 12 | [Qwen3 Max](/models/qwen3-max) | — | Alibaba | 68.03% |
| 13 | [Grok 4.5](/models/grok-4-5) | high reasoning | xAI | 67.41% |
| 14 | [Claude Opus 4.6 (Adaptive)](/models/claude-opus-4-6-thinking) | — | Anthropic | 67.02% |
| 15 | [Claude Sonnet 5](/models/claude-sonnet-5) | — | Anthropic | 66.98% |
| 16 | [Grok 4 Fast (Reasoning)](/models/grok-4-fast-reasoning) | — | xAI | 66.90% |
| 17 | [Kimi K2.6](/models/kimi-2-6) | — | Moonshot AI | 66.74% |
| 18 | [Claude Opus 4.8](/models/claude-opus-4-8) | — | Anthropic | 66.71% |
| 19 | [Qwen 3.6 Max (preview)](/models/qwen3-6-max-preview) | — | Alibaba | 66.47% |
| 20 | [Gemini 3 Flash Preview](https://www.vals.ai/models/google_gemini-3-flash-preview) | high reasoning | Google | 66.43% |
| 21 | [Grok 4.6](/models/grok-4-6) | high reasoning | xAI | 66.16% |
| 22 | [GLM-5.2](/models/glm-5-2) | — | Z.AI | 66.12% |
| 23 | [Claude Opus 4.7](/models/claude-opus-4-7) | — | Anthropic | 66.08% |
| 24 | [Grok 4 0709](https://www.vals.ai/models/grok_grok-4-0709) | — | xAI | 66.05% |
| 25 | [Grok 4.1 Fast (Reasoning)](/models/grok-4-1-fast-reasoning) | — | xAI | 65.97% |
| 26 | [GPT-5.2](/models/gpt-5-2) | xhigh reasoning | OpenAI | 65.89% |
| 27 | [Qwen3.8 Max](/models/qwen3-8-max) | — | Alibaba | 65.85% |
| 28 | [Nemotron 3 Ultra 550b A55b](https://www.vals.ai/models/nvidia_nemotron-3-ultra-550b-a55b) | — | Nvidia | 65.46% |
| 29 | [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | max reasoning | DeepSeek | 65.42% |
| 30 | [GPT-5.6 Terra](/models/gpt-5-6-terra) | xhigh reasoning | OpenAI | 65.31% |
| 31 | [Claude Sonnet 4.6](/models/claude-sonnet-4-6) | — | Anthropic | 65.31% |
| 32 | [Qwen3.5 Plus Thinking](https://www.vals.ai/models/alibaba_qwen3.5-plus-thinking) | — | Alibaba | 65.31% |
| 33 | [GPT-5.4](/models/gpt-5-4) | xhigh reasoning | OpenAI | 65.27% |
| 34 | [Muse Spark](/models/muse-spark) | — | Meta | 65.11% |
| 35 | [Claude Opus 4.5 Thinking](/models/claude-opus-4-5-thinking) | — | Anthropic | 65.07% |
| 36 | [Gemini 3.5 Flash](/models/gemini-3-5-flash) | high reasoning | Google | 64.69% |
| 37 | [Gemini 3.1 Pro Preview](https://www.vals.ai/models/google_gemini-3.1-pro-preview) | high reasoning | Google | 64.49% |
| 38 | [GLM-5.1](/models/glm-5-1) | — | Z.AI | 64.45% |
| 39 | [GPT-5.6 Sol](/models/gpt-5-6-sol) | max reasoning | OpenAI | 64.38% |
| 40 | [GPT-5.6 Luna](/models/gpt-5-6-luna) | max reasoning | OpenAI | 64.22% |
| 41 | [GPT-5.1](/models/gpt-5-1) | high reasoning | OpenAI | 63.83% |
| 42 | [Qwen3.7 Max](/models/qwen3-7-max) | — | Alibaba | 63.71% |
| 43 | [Grok 4.20 0309 Reasoning](https://www.vals.ai/models/grok_grok-4.20-0309-reasoning) | — | xAI | 63.67% |
| 44 | [Gemini 3 Pro Preview](https://www.vals.ai/models/google_gemini-3-pro-preview) | high reasoning | Google | 63.67% |
| 45 | [Qwen3.5 Flash](/models/qwen3-5-flash) | — | Alibaba | 63.56% |
| 46 | [Gemini 3.6 Flash](/models/gemini-3-6-flash) | high reasoning | Google | 63.33% |
| 47 | [GPT-4.1](/models/gpt-4-1) | high reasoning | OpenAI | 63.05% |
| 48 | [GLM 5 Thinking](https://www.vals.ai/models/zai_glm-5-thinking) | — | Zhipu AI | 62.90% |
| 49 | [Qwen3.6-27B](/models/qwen3-6-27b) | — | Alibaba | 62.31% |
| 50 | [Claude Sonnet 4.5 Thinking](/models/claude-sonnet-4-5-thinking) | — | Anthropic | 61.97% |
| 51 | [Ling 3.0 Flash 2607](https://www.vals.ai/models/ant_ling-3.0-flash-2607) | — | Ant | 61.93% |
| 52 | [Qwen3.6 Plus](/models/qwen3-6-plus) | — | Alibaba | 61.93% |
| 53 | [DeepSeek V4 Flash 0731](/models/deepseek-v4-flash-0731) | high reasoning | DeepSeek | 61.85% |
| 54 | [MiMo-V2.5-Pro](/models/mimo-v2-5-pro) | — | Xiaomi | 61.42% |
| 55 | [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | max reasoning | DeepSeek | 61.38% |
| 56 | [Claude Opus 4.5](/models/claude-opus-4-5) | — | Anthropic | 61.30% |
| 57 | [Claude Sonnet 4 20250514 Thinking](https://www.vals.ai/models/anthropic_claude-sonnet-4-20250514-thinking) | — | Anthropic | 61.23% |
| 58 | [GPT-5.4 nano](/models/gpt-5-4-nano) | high reasoning | OpenAI | 61.19% |
| 59 | [MiniMax M2.7](/models/minimax-m2-7) | — | MiniMax | 61.19% |
| 60 | [Grok 3 Mini Fast High Reasoning](https://www.vals.ai/models/grok_grok-3-mini-fast-high-reasoning) | high reasoning | xAI | 61.11% |
| 61 | [GPT-5](https://www.vals.ai/models/openai_gpt-5-2025-08-07) | high reasoning | OpenAI | 61.07% |
| 62 | [Mistral Large 2512](https://www.vals.ai/models/mistralai_mistral-large-2512) | — | Mistral AI | 61.03% |
| 63 | [GLM-4.5](/models/glm-4-5) | — | Z.AI | 60.96% |
| 64 | [GPT-5.4 mini](/models/gpt-5-4-mini) | xhigh reasoning | OpenAI | 60.92% |
| 65 | [Claude Sonnet 4.5](/models/claude-sonnet-4-5) | — | Anthropic | 60.80% |
| 66 | [Gemini 2.5 Pro](/models/gemini-2-5-pro) | — | Google | 60.80% |
| 67 | [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite) | high reasoning | Google | 60.68% |
| 68 | [Claude Haiku 4.5 Thinking](/models/claude-haiku-4-5-thinking) | — | Anthropic | 60.61% |
| 69 | [Kimi K2 Thinking](https://www.vals.ai/models/kimi_kimi-k2-thinking) | — | Moonshot AI | 60.57% |
| 70 | [Claude 3.7 Sonnet 20250219 Thinking](https://www.vals.ai/models/anthropic_claude-3-7-sonnet-20250219-thinking) | — | Anthropic | 60.41% |
| 71 | [Claude Haiku 4.5](/models/claude-haiku-4-5) | — | Anthropic | 60.30% |
| 72 | [GPT-5 mini](/models/gpt-5-mini) | high reasoning | OpenAI | 60.18% |
| 73 | [MiMo-V2.5](/models/mimo-v2-5) | — | Xiaomi | 59.91% |
| 74 | [Gemini 2.5 Pro Exp 03 25](https://www.vals.ai/models/google_gemini-2.5-pro-exp-03-25) | — | Google | 59.83% |
| 75 | [Gemini 2.5 Flash Preview 09 2025 Thinking](https://www.vals.ai/models/google_gemini-2.5-flash-preview-09-2025-thinking) | — | Google | 59.75% |
| 76 | [o3](/models/o3) | high reasoning | OpenAI | 59.71% |
| 77 | [Grok 3](https://www.vals.ai/models/grok_grok-3) | — | xAI | 59.71% |
| 78 | [MiniMax M2.5](/models/minimax-m2-5) | — | MiniMax | 59.60% |
| 79 | [Grok 3 Mini Fast Low Reasoning](https://www.vals.ai/models/grok_grok-3-mini-fast-low-reasoning) | low reasoning | xAI | 59.48% |
| 80 | [Gemini 3.1 Flash Lite Preview](https://www.vals.ai/models/google_gemini-3.1-flash-lite-preview) | high reasoning | Google | 59.36% |
| 81 | [O4 Mini](https://www.vals.ai/models/openai_o4-mini-2025-04-16) | high reasoning | OpenAI | 58.97% |
| 82 | [Gemini 2.5 Flash Preview 09 2025](https://www.vals.ai/models/google_gemini-2.5-flash-preview-09-2025) | — | Google | 58.97% |
| 83 | [MiniMax M2.1](https://www.vals.ai/models/minimax_MiniMax-M2.1) | — | MiniMax | 58.90% |
| 84 | [Mistral Medium 3.5](https://www.vals.ai/models/mistralai_mistral-medium-3.5) | high reasoning | Mistral AI | 58.78% |
| 85 | [Grok 4 Fast Non Reasoning](https://www.vals.ai/models/grok_grok-4-fast-non-reasoning) | — | xAI | 58.39% |
| 86 | [GPT-OSS 120B](/models/gpt-oss-120b) | — | OpenAI | 58.24% |
| 87 | [Laguna M.1](/models/laguna-m-1) | — | Poolside | 58.16% |
| 88 | [GPT-4.1 mini](/models/gpt-4-1-mini) | high reasoning | OpenAI | 57.93% |
| 89 | [Gemini 2.5 Flash Lite Preview 09 2025 Thinking](https://www.vals.ai/models/google_gemini-2.5-flash-lite-preview-09-2025-thinking) | — | Google | 57.58% |
| 90 | [GLM-4.6](/models/glm-4-6) | — | Z.AI | 56.84% |
| 91 | [Laguna XS.2](/models/laguna-xs-2) | — | Poolside | 56.33% |
| 92 | [Gemini 2.5 Flash Lite Preview 09 2025](https://www.vals.ai/models/google_gemini-2.5-flash-lite-preview-09-2025) | — | Google | 56.29% |
| 93 | [Qwen3 Max](/models/qwen3-max) | — | Alibaba | 55.94% |
| 94 | [DeepSeek V3 0324](https://www.vals.ai/models/fireworks_deepseek-v3-0324) | — | Fireworks AI | 54.74% |
| 95 | [Claude Sonnet 4](https://www.vals.ai/models/anthropic_claude-sonnet-4-20250514) | — | Anthropic | 54.70% |
| 96 | [Trinity-Large-Thinking](/models/trinity-large-thinking) | — | Arcee AI | 54.66% |
| 97 | [Nemotron Lightning 3p5 30b A3b](https://www.vals.ai/models/fireworks_nemotron-lightning-3p5-30b-a3b) | — | Fireworks AI | 54.23% |
| 98 | [Gemini 2.5 Flash Preview 04 17](https://www.vals.ai/models/google_gemini-2.5-flash-preview-04-17) | — | Google | 54.16% |
| 99 | [DeepSeek-R1](/models/deepseek-r1) | — | DeepSeek | 54.12% |
| 100 | [Claude 3.5 Sonnet](/models/claude-3-5-sonnet) | — | Anthropic | 53.61% |
| 101 | [GPT-OSS 20B](/models/gpt-oss-20b) | — | OpenAI | 53.15% |
| 102 | [Qwen3 Max Preview](https://www.vals.ai/models/alibaba_qwen3-max-preview) | — | Alibaba | 52.95% |
| 103 | [Grok 4.1 Fast Non Reasoning](https://www.vals.ai/models/grok_grok-4-1-fast-non-reasoning) | — | xAI | 52.49% |
| 104 | [DeepSeek V3](/models/deepseek-v3) | — | DeepSeek | 52.49% |
| 105 | [DeepSeek V3p1](https://www.vals.ai/models/fireworks_deepseek-v3p1) | — | Fireworks AI | 51.48% |
| 106 | [Grok 2 1212](https://www.vals.ai/models/grok_grok-2-1212) | — | xAI | 51.13% |
| 107 | [DeepSeek V3p2 Thinking](https://www.vals.ai/models/fireworks_deepseek-v3p2-thinking) | high reasoning | Fireworks AI | 50.97% |
| 108 | [Claude 3.5 Haiku](https://www.vals.ai/models/anthropic_claude-3-5-haiku-20241022) | — | Anthropic | 50.82% |
| 109 | [Mistral Medium 2505](https://www.vals.ai/models/mistralai_mistral-medium-2505) | — | Mistral AI | 50.74% |
| 110 | [Moonshotai Kimi K2 Instruct](https://www.vals.ai/models/together_moonshotai/Kimi-K2-Instruct) | — | Together AI | 50.39% |
| 111 | [Llama4 Maverick Instruct Basic](https://www.vals.ai/models/fireworks_llama4-maverick-instruct-basic) | — | Fireworks AI | 49.73% |
| 112 | [DeepSeek V3p2](https://www.vals.ai/models/fireworks_deepseek-v3p2) | none reasoning | Fireworks AI | 47.94% |
| 113 | [Magistral Medium 2509](https://www.vals.ai/models/mistralai_magistral-medium-2509) | — | Mistral AI | 47.40% |
| 114 | [Meta Llama Llama 4 Scout 17B 16E Instruct](https://www.vals.ai/models/together_meta-llama/Llama-4-Scout-17B-16E-Instruct) | — | Together AI | 46.78% |
| 115 | [GLM-4.7](/models/glm-4-7) | — | Z.AI | 46.39% |
| 116 | [Command A 03 2025](https://www.vals.ai/models/cohere_command-a-03-2025) | — | Cohere | 45.96% |
| 117 | [GPT-4o](/models/gpt-4o) | high reasoning | OpenAI | 45.92% |
| 118 | [GPT-4o mini](/models/gpt-4o-mini) | high reasoning | OpenAI | 45.45% |
| 119 | [o3-mini](/models/o3-mini) | high reasoning | OpenAI | 45.30% |
| 120 | [Mistral Small 2503](https://www.vals.ai/models/mistralai_mistral-small-2503) | — | Mistral AI | 44.17% |
| 121 | [Magistral Small 2509](https://www.vals.ai/models/mistralai_magistral-small-2509) | — | Mistral AI | 44.02% |
| 122 | [Gemini 2.0 Pro Exp 02 05](https://www.vals.ai/models/google_gemini-2.0-pro-exp-02-05) | — | Google | 43.44% |
| 123 | [GPT-4.1 nano](/models/gpt-4-1-nano) | high reasoning | OpenAI | 42.08% |
| 124 | [Jamba Large 1.6](https://www.vals.ai/models/ai21labs_jamba-large-1.6) | — | AI21 Labs | 41.53% |
| 125 | [Gemini 1.5 Pro 002](https://www.vals.ai/models/google_gemini-1.5-pro-002) | — | Google | 40.52% |
| 126 | [GPT-4o](/models/gpt-4o) | high reasoning | OpenAI | 39.43% |
| 127 | [Jamba 1.5 Large](https://www.vals.ai/models/ai21labs_jamba-1.5-large) | — | AI21 Labs | 39.43% |
| 128 | [Meta Llama Meta Llama 3.1 70B Instruct Turbo](https://www.vals.ai/models/together_meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo) | — | Together AI | 38.85% |
| 129 | [Gemini 1.5 Flash 002](https://www.vals.ai/models/google_gemini-1.5-flash-002) | — | Google | 38.19% |
| 130 | [Jamba Mini 1.6](https://www.vals.ai/models/ai21labs_jamba-mini-1.6) | — | AI21 Labs | 38.03% |
| 131 | [Meta Llama Meta Llama 3.1 8B Instruct Turbo](https://www.vals.ai/models/together_meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo) | — | Together AI | 37.80% |
| 132 | [Jamba 1.5 Mini](https://www.vals.ai/models/ai21labs_jamba-1.5-mini) | — | AI21 Labs | 33.88% |
| 133 | [Gemini 2.0 Flash 001](https://www.vals.ai/models/google_gemini-2.0-flash-001) | — | Google | 33.72% |
| 134 | [Gemini 1.5 Flash 001](https://www.vals.ai/models/google_gemini-1.5-flash-001) | — | Google | 28.63% |

## FAQ

### What does CorpFin v2 measure?

Vals AI private benchmark for understanding long-context credit agreements.

### Which model leads the published CorpFin v2 snapshot?

Claude Opus 5 currently leads the published CorpFin v2 snapshot with a score of 73.19%.

### How many models are evaluated on CorpFin v2?

The August 12, 2026 contains 134 AI models.

### Does CorpFin v2 affect BenchLM's overall score?

Not directly. CorpFin v2 is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.