Massive Multitask Language Understanding — tests knowledge across 57 subjects.
Data from LayerLens
As of November 21, 2026, the top-scoring model on MMLU is Qwen3.7 Max at 93.7%, followed by GPT-5 at 93.5% and o3 at 93.1%. 69 models have been evaluated on this benchmark.
Last updated: November 21, 2026
Models
69
Best Score
93.7
Average
82.8
Std Dev
13.0
Provider | Model | Input $/M | Output $/M | MMLU | Actions |
|---|---|---|---|---|---|
$1.475 | $4.425 | 93.7 | |||
$1.250 | $10.000 | 93.5 | |||
$2.000 | $8.000 | 93.1 | |||
$0.390 | $0.900 | 92.7 | |||
$0.260 | $1.560 | 92.5 | |||
$0.320 | $1.400 | 91.9 | |||
$0.320 | $1.400 | 91.9 | |||
$0.260 | $0.900 | 91.8 | |||
$0.600 | $1.920 | 91.7 | |||
$0.600 | $1.920 | 91.7 | |||
$0.195 | $0.900 | 91.5 | |||
$0.065 | $0.750 | 90.7 | |||
$0.065 | $0.260 | 90.7 | |||
$0.500 | $2.150 | 90.5 | |||
$0.125 | $1.000 | 90.5 | |||
$0.900 | $0.900 | 90.3 | |||
$0.075 | $0.400 | 90.2 | |||
$0.450 | $0.900 | 90.2 | |||
$0.600 | $2.200 | 90.0 | |||
$0.100 | $0.100 | 89.0 | |||
$1.250 | $7.500 | 89.0 | |||
$0.900 | $0.900 | 88.7 | |||
$0.900 | $0.900 | 88.7 | |||
$0.550 | $2.200 | 88.3 | |||
$0.270 | $0.950 | 88.1 | |||
$0.780 | $3.900 | 87.6 | |||
$0.030 | $0.100 | 87.6 | |||
$0.050 | $0.190 | 87.1 | |||
$0.200 | $0.900 | 86.8 | |||
$0.025 | $0.200 | 86.8 | |||
$0.600 | $2.500 | 86.2 | |||
$1.750 | $14.000 | 86.1 | |||
$0.250 | $0.750 | 86.0 | |||
$0.090 | $0.900 | 85.8 | |||
$0.200 | $0.880 | 85.8 | |||
$0.300 | $2.500 | 85.7 | |||
$0.300 | $2.500 | 85.7 | |||
$0.200 | $0.600 | 85.5 | |||
$0.625 | $5.000 | 85.5 | |||
$0.120 | $0.500 | 85.3 | |||
$0.120 | $0.500 | 85.3 | |||
$0.000 | $0.000 | 85.2 | |||
$0.500 | $1.500 | 85.2 | |||
$2.000 | $8.000 | 84.6 | |||
$2.500 | $10.000 | 84.1 | |||
$0.300 | $0.900 | 83.8 | |||
$0.060 | $0.400 | 83.7 | |||
$0.060 | $0.400 | 83.7 | |||
$0.014 | $0.028 | 83.4 | |||
$0.130 | $0.850 | 82.9 | |||
$0.440 | $2.200 | 82.6 | |||
$0.375 | $2.250 | 81.8 | |||
$0.288 | $0.320 | 81.2 | |||
$0.000 | $0.000 | 79.2 | |||
$0.800 | $3.200 | 78.3 | |||
$1.000 | $3.000 | 77.7 | |||
$1.000 | $3.000 | 77.7 | |||
$0.070 | $0.280 | 77.6 | |||
$0.070 | $0.140 | 77.6 | |||
$0.075 | $0.200 | 76.0 | |||
$0.100 | $0.280 | 73.3 | |||
$0.060 | $0.240 | 72.7 | |||
$0.035 | $0.140 | 68.9 | |||
$0.080 | $0.200 | 66.1 | |||
$0.080 | $0.200 | 66.1 | |||
$0.100 | $0.625 | 65.4 | |||
$0.020 | $0.040 | 63.8 | |||
$0.100 | $0.300 | 24.6 | |||
$0.030 | $0.050 | 15.3 |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
Massive Multitask Language Understanding — tests knowledge across 57 subjects.
This leaderboard shows all models with MMLU 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.