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
Models
8
Best Score
44.8
Average
22.1
Std Dev
11.7
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.
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.
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.