BIRD-CRITIC — multi-turn benchmark testing SQL generation and database interaction.
Data from LayerLens
As of November 21, 2026, the top-scoring model on BIRD-CRITIC is Claude Opus 4.7 at 36.3%, followed by Claude Opus 4.6 at 34.0% and Claude Opus 4.6 at 34.0%. 22 models have been evaluated on this benchmark.
Last updated: November 21, 2026
Models
22
Best Score
36.3
Average
29.2
Std Dev
4.1
Provider | Model | Input $/M | Output $/M | BIRD-CRITIC | Actions |
|---|---|---|---|---|---|
$5.000 | $25.000 | 36.3 | |||
$5.000 | $25.000 | 34.0 | |||
$5.000 | $25.000 | 34.0 | |||
$0.000 | $0.000 | 33.3 | |||
$0.320 | $1.400 | 33.0 | |||
$0.320 | $1.400 | 33.0 | |||
$0.014 | $0.029 | 32.7 | |||
$0.490 | $2.500 | 31.3 | |||
$0.490 | $2.500 | 31.3 | |||
$0.300 | $0.900 | 31.0 | |||
$0.000 | $0.000 | 30.9 | |||
$0.300 | $2.500 | 29.7 | |||
$0.300 | $2.500 | 29.7 | |||
$0.030 | $0.100 | 25.8 | |||
$0.080 | $0.160 | 25.8 | |||
$0.300 | $0.900 | 25.3 | |||
$0.300 | $0.900 | 25.3 | |||
$0.500 | $1.500 | 25.0 | |||
$0.060 | $0.400 | 25.0 | |||
$0.060 | $0.400 | 25.0 | |||
$0.060 | $0.240 | 22.7 | |||
$0.060 | $0.240 | 22.7 |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
BIRD-CRITIC — multi-turn benchmark testing SQL generation and database interaction.
This leaderboard shows all models with BIRD-CRITIC 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.