GAIA Leaderboard

GAIA — General AI Assistants benchmark testing multi-step real-world tasks.

Data from LayerLens

As of November 21, 2026, the top-scoring model on GAIA is GPT-5 Mini at 44.8%, followed by Gemini 2.5 Pro at 33.3% and R1 0528 at 27.9%. 8 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

8

Best Score

44.8

Average

22.1

Std Dev

11.7

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
GAIA
Actions
$0.125
$1.000
44.8
$1.000
$10.000
33.3
$0.500
$2.150
27.9
$0.440
$2.200
23.3
$0.064
$0.224
12.3
$0.064
$0.224
12.3
$0.250
$0.950
11.5
$0.250
$0.950
11.5

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About GAIA

GAIA — General AI Assistants benchmark testing multi-step real-world tasks.

This leaderboard shows all models with GAIA benchmark scores, ranked from highest to lowest. Pricing data is included to help you compare performance against cost.

Frequently Asked Questions

GAIA — General AI Assistants benchmark testing multi-step real-world tasks.
As of November 21, 2026, GPT-5 Mini leads the GAIA leaderboard with a score of 44.8. Rankings change as new models are released and evaluated.
Currently 8 models have been evaluated on GAIA, with an average score of 22.1 and standard deviation of 11.7.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.