Benchmark library

Explore every benchmark.

Benchmark definitions
10 benchmark definitions
Published rankings
9 published rankings
Defined tasks
680 defined tasks

Recognize recurring models by color, scan the strongest ten observed results, then open a benchmark for every published model and its exact run evidence.

Accounting, Reporting & Financial Analysis

14 models

Accounting Capstone

100 tasks · Hybrid scoring · Provisional

Top 10 published results for Accounting Capstone

  1. 01Kimi K2.691.9
  2. 02Claude Opus 589.7
  3. 03GPT-5.6 Terra89.5
  4. 04Kimi K388.7
  5. 05Gemini 3.5 Flash83.3
  6. 06Claude Sonnet 5 (Max)81.0
  7. 07DeepSeek V4 Flash77.6
  8. 08Grok 4.574.2
  9. 09Qwen3.6-35B-A3B72.2
  10. 10NVIDIA Nemotron 3 Ultra37.2

Corporate Finance & Valuation

In development

Corporate Finance Capstone

100 tasks · Hybrid scoring

Calibration pending

Results will appear here after a compatible public calibration release is published.

Accounting, Reporting & Financial Analysis

14 models

Accounting Knowledge

60 tasks · Hybrid scoring · Provisional

Top 10 published results for Accounting Knowledge

  1. 01GLM 5.296.0
  2. 02Grok 4.595.9
  3. 03DeepSeek V4 Flash95.0
  4. 04Kimi K2.694.7
  5. 05Qwen3.6-35B-A3B93.3
  6. 06Claude Sonnet 5 (Max)93.2
  7. 07Claude Opus 592.4
  8. 08Kimi K391.7
  9. 09GPT-5.6 Terra90.6
  10. 10Gemini 3.5 Flash90.3

Accounting, Reporting & Financial Analysis

14 models

HGB Reporting

60 tasks · Deterministic scoring · Provisional

Top 10 published results for HGB Reporting

  1. 01Gemini 3.5 Flash92.4
  2. 02Grok 4.590.7
  3. 03GPT-5.6 Terra90.2
  4. 04Kimi K2.690.2
  5. 05Qwen3.6-35B-A3B89.4
  6. 06MiniMax M389.3
  7. 07Kimi K388.4
  8. 08Mistral Large 251287.6
  9. 09Claude Opus 586.5
  10. 10Claude Sonnet 5 (Max)85.6

Accounting, Reporting & Financial Analysis

14 models

IFRS Reporting

60 tasks · Deterministic scoring · Provisional

Top 10 published results for IFRS Reporting

  1. 01Gemini 3.5 Flash91.9
  2. 02GPT-5.6 Terra91.9
  3. 03Grok 4.591.4
  4. 04Kimi K391.4
  5. 05Kimi K2.691.1
  6. 06GLM 5.291.0
  7. 07Claude Sonnet 5 (Max)90.8
  8. 08Qwen3.6-35B-A3B90.7
  9. 09DeepSeek V4 Flash90.6
  10. 10NVIDIA Nemotron 3 Ultra89.7

Accounting, Reporting & Financial Analysis

14 models

Financial Analysis

60 tasks · Deterministic scoring · Provisional

Top 10 published results for Financial Analysis

  1. 01MiniMax M391.9
  2. 02Kimi K2.687.5
  3. 03GPT-5.6 Terra82.0
  4. 04Claude Opus 579.4
  5. 05Llama 4 Maverick78.3
  6. 06Gemini 3.5 Flash77.8
  7. 07Qwen3.6-35B-A3B77.1
  8. 08GLM 5.267.7
  9. 09Kimi K366.5
  10. 10Mistral Large 251263.4

Corporate Finance & Valuation

14 models

Capital Budgeting

60 tasks · Deterministic scoring · Provisional

Top 10 published results for Capital Budgeting

  1. 01Kimi K386.7
  2. 02Claude Sonnet 5 (Max)81.7
  3. 03GPT-5.6 Terra81.7
  4. 04Claude Opus 580.0
  5. 05DeepSeek V4 Flash76.7
  6. 06Kimi K2.665.0
  7. 07Qwen3.6-35B-A3B60.0
  8. 08Grok 4.558.3
  9. 09Gemini 3.5 Flash55.0
  10. 10GLM 5.211.7

Corporate Finance & Valuation

14 models

Cost of Capital & Financing

60 tasks · Deterministic scoring · Provisional

Top 10 published results for Cost of Capital & Financing

  1. 01Kimi K2.693.3
  2. 02Kimi K391.7
  3. 03Claude Opus 586.7
  4. 04Claude Sonnet 5 (Max)85.0
  5. 05DeepSeek V4 Flash85.0
  6. 06Gemini 3.5 Flash81.7
  7. 07Qwen3.6-35B-A3B80.0
  8. 08GPT-5.6 Terra76.7
  9. 09Grok 4.573.3
  10. 10NVIDIA Nemotron 3 Ultra30.0

Corporate Finance & Valuation

14 models

Valuation & Financial Modeling

60 tasks · Deterministic scoring · Provisional

Top 10 published results for Valuation & Financial Modeling

  1. 01Claude Sonnet 5 (Max)100.0
  2. 02Gemini 3.5 Flash98.3
  3. 03Claude Opus 596.7
  4. 04GPT-5.6 Terra96.7
  5. 05DeepSeek V4 Flash95.0
  6. 06Kimi K395.0
  7. 07Kimi K2.688.3
  8. 08Qwen3.6-35B-A3B86.7
  9. 09Grok 4.575.0
  10. 10NVIDIA Nemotron 3 Ultra40.0

Corporate Finance & Valuation

14 models

M&A, LBO & Capital Allocation

60 tasks · Deterministic scoring · Provisional

Top 10 published results for M&A, LBO & Capital Allocation

  1. 01Kimi K3100.0
  2. 02Claude Sonnet 5 (Max)98.3
  3. 03Gemini 3.5 Flash98.3
  4. 04Kimi K2.698.3
  5. 05Claude Opus 596.7
  6. 06DeepSeek V4 Flash96.7
  7. 07GPT-5.6 Terra96.7
  8. 08Grok 4.591.7
  9. 09Qwen3.6-35B-A3B91.7
  10. 10GLM 5.261.7