Accounting Audit Leaderboard

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

8 Ways to Use Fewer Tokens

Models

32

Best Score

83.3

Average

74.2

Std Dev

10.4

Categories
Financial Reasoning
Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
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.

About Accounting Audit

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.

Frequently Asked Questions

Accounting and audit benchmark testing financial reasoning capabilities.
As of November 21, 2026, GPT-4.1 leads the Accounting Audit leaderboard with a score of 83.3. Rankings change as new models are released and evaluated.
Currently 32 models have been evaluated on Accounting Audit, with an average score of 74.2 and standard deviation of 10.4.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.