Accounting and audit benchmark testing financial reasoning capabilities.
Data from LayerLens
As of November 21, 2026, the top-scoring model on Accounting Audit is GPT-4.1 at 83.3%, followed by Gemini 2.5 Flash at 83.3% and Gemini 2.5 Flash at 83.3%. 32 models have been evaluated on this benchmark.
Last updated: November 21, 2026
Models
32
Best Score
83.3
Average
74.2
Std Dev
10.4
Provider | Model | Input $/M | Output $/M | Accounting Audit | Actions |
|---|---|---|---|---|---|
$2.000 | $8.000 | 83.3 | |||
$0.300 | $2.500 | 83.3 | |||
$0.300 | $2.500 | 83.3 | |||
$1.250 | $10.000 | 83.3 | |||
$0.014 | $0.028 | 80.0 | |||
$0.200 | $0.600 | 80.0 | |||
$0.080 | $0.200 | 80.0 | |||
$0.080 | $0.200 | 80.0 | |||
$0.120 | $0.500 | 80.0 | |||
$0.120 | $0.500 | 80.0 | |||
$0.500 | $2.150 | 80.0 | |||
$0.320 | $1.400 | 80.0 | |||
$0.320 | $1.400 | 80.0 | |||
$0.000 | $0.000 | 76.7 | |||
$0.800 | $3.200 | 76.7 | |||
$0.900 | $0.900 | 76.7 | |||
$0.900 | $0.900 | 76.7 | |||
$0.064 | $0.224 | 76.7 | |||
$0.064 | $0.224 | 76.7 | |||
$0.000 | $0.000 | 76.7 | |||
$0.780 | $3.900 | 76.7 | |||
$0.550 | $2.190 | 73.3 | |||
$0.440 | $2.200 | 73.3 | |||
$1.000 | $5.000 | 73.3 | |||
$1.000 | $5.000 | 73.3 | |||
$0.100 | $0.280 | 70.0 | |||
$2.500 | $10.000 | 70.0 | |||
$0.100 | $0.300 | 70.0 | |||
$0.070 | $0.140 | 66.7 | |||
$0.035 | $0.140 | 53.3 | |||
$0.030 | $0.050 | 50.0 | |||
$0.080 | $0.160 | 33.3 |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
Accounting and audit benchmark testing financial reasoning capabilities.
This leaderboard shows all models with Accounting Audit benchmark scores, ranked from highest to lowest. Pricing data is included to help you compare performance against cost.
Built by @aellman
Also from the founder: BlobCap, a price index for AI training data deals, showing what AI labs actually pay for data.
2026 68 Ventures, LLC. All rights reserved.