BIRD-CRITIC Leaderboard

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

8 Ways to Use Fewer Tokens

Models

22

Best Score

36.3

Average

29.2

Std Dev

4.1

Categories
Multi-turn
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
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.

About BIRD-CRITIC

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.

Frequently Asked Questions

BIRD-CRITIC — multi-turn benchmark testing SQL generation and database interaction.
As of November 21, 2026, Claude Opus 4.7 leads the BIRD-CRITIC leaderboard with a score of 36.3. Rankings change as new models are released and evaluated.
Currently 22 models have been evaluated on BIRD-CRITIC, with an average score of 29.2 and standard deviation of 4.1.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.