Stock market benchmark testing financial analysis capabilities.
Data from LayerLens
As of November 21, 2026, the top-scoring model on Stock BCS is Qwen2.5 72B Instruct at 100.0%, followed by GPT-4.1 at 91.7% and Qwen3 235B A22B at 83.3%. 16 models have been evaluated on this benchmark.
Last updated: November 21, 2026
Models
16
Best Score
100.0
Average
56.2
Std Dev
34.3
Provider | Model | Input $/M | Output $/M | Stock BCS | Actions |
|---|---|---|---|---|---|
$0.288 | $0.320 | 100.0 | |||
$2.000 | $8.000 | 91.7 | |||
$0.900 | $0.900 | 83.3 | |||
$0.900 | $0.900 | 83.3 | |||
$0.120 | $0.500 | 83.3 | |||
$0.120 | $0.500 | 83.3 | |||
$0.064 | $0.224 | 75.0 | |||
$0.064 | $0.224 | 75.0 | |||
$0.014 | $0.028 | 66.7 | |||
$0.300 | $2.500 | 58.3 | |||
$0.300 | $2.500 | 58.3 | |||
$0.800 | $3.200 | 25.0 | |||
$0.030 | $0.050 | 8.3 | |||
$0.070 | $0.140 | 8.3 | |||
$0.100 | $0.300 | - | |||
$0.200 | $0.600 | - |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
Stock market benchmark testing financial analysis capabilities.
This leaderboard shows all models with Stock BCS 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.