Extended formal logic benchmark testing deductive and propositional reasoning.
Data from LayerLens
As of November 21, 2026, the top-scoring model on Formal Logic Extended is R1 0528 at 99.2%, followed by GPT-4.1 at 90.6% and DeepSeek V3 at 83.6%. 8 models have been evaluated on this benchmark.
Last updated: November 21, 2026
Models
8
Best Score
99.2
Average
53.4
Std Dev
38.3
Provider | Model | Input $/M | Output $/M | Formal Logic Extended | Actions |
|---|---|---|---|---|---|
$0.500 | $2.150 | 99.2 | |||
$2.000 | $8.000 | 90.6 | |||
$0.014 | $0.028 | 83.6 | |||
$2.500 | $10.000 | 80.7 | |||
$0.030 | $0.050 | 52.2 | |||
$0.200 | $0.600 | 10.8 | |||
$0.070 | $0.140 | 9.7 | |||
$0.100 | $0.300 | 0.1 |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
Extended formal logic benchmark testing deductive and propositional reasoning.
This leaderboard shows all models with Formal Logic Extended 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.