Multimodal Understanding benchmark testing vision-language models on expert-level tasks.
Data from LayerLens
As of November 21, 2026, the top-scoring model on MMMU is Gemini 3.1 Pro Preview at 83.8%, followed by GPT-5.5 at 83.0% and Gemini 3.5 Flash at 83.0%. 83 models have been evaluated on this benchmark.
Last updated: November 21, 2026
Models
83
Best Score
83.8
Average
61.3
Std Dev
20.7
Provider | Model | Input $/M | Output $/M | MMMU | Actions |
|---|---|---|---|---|---|
$1.000 | $6.000 | 83.8 | |||
$5.000 | $30.000 | 83.0 | |||
$1.500 | $9.000 | 83.0 | |||
$0.750 | $3.750 | 82.9 | |||
$0.500 | $3.000 | 82.8 | |||
$0.500 | $3.000 | 81.7 | |||
$2.000 | $6.000 | 81.6 | |||
$0.040 | $0.078 | 81.4 | |||
$0.490 | $2.500 | 79.3 | |||
$0.490 | $2.500 | 79.3 | |||
$0.230 | $0.960 | 79.3 | |||
$1.250 | $10.000 | 79.1 | |||
$0.260 | $0.900 | 78.1 | |||
$0.200 | $1.200 | 77.7 | |||
$0.195 | $0.900 | 77.6 | |||
$0.030 | $0.130 | 77.4 | |||
$5.000 | $25.000 | 77.3 | |||
$5.000 | $25.000 | 77.3 | |||
$0.188 | $1.125 | 77.0 | |||
$0.065 | $0.260 | 76.8 | |||
$0.216 | $0.647 | 76.7 | |||
$5.000 | $25.000 | 76.6 | |||
$0.065 | $0.750 | 76.4 | |||
$2.000 | $8.000 | 76.3 | |||
$5.000 | $25.000 | 76.3 | |||
$5.000 | $25.000 | 76.3 | |||
$0.050 | $0.700 | 75.9 | |||
$5.000 | $25.000 | 75.4 | |||
$0.125 | $1.000 | 75.3 | |||
$3.000 | $15.000 | 75.3 | |||
$0.300 | $2.500 | 74.4 | |||
$0.080 | $0.120 | 74.1 | |||
$0.100 | $0.100 | 74.1 | |||
$0.300 | $0.900 | 74.1 | |||
$0.250 | $1.500 | 73.7 | |||
$3.000 | $15.000 | 72.9 | |||
$0.050 | $0.190 | 71.8 | |||
$3.000 | $15.000 | 71.7 | |||
$0.300 | $0.900 | 71.1 | |||
$0.300 | $0.900 | 71.1 | |||
$0.025 | $0.200 | 70.7 | |||
$2.000 | $8.000 | 69.3 | |||
$0.200 | $0.880 | 68.2 | |||
$1.000 | $5.000 | 65.2 | |||
$1.000 | $5.000 | 65.2 | |||
$1.500 | $7.500 | 64.4 | |||
$0.500 | $1.500 | 63.0 | |||
$1.750 | $14.000 | 62.3 | |||
$1.250 | $7.500 | 61.6 | |||
$0.625 | $5.000 | 60.7 | |||
$2.500 | $10.000 | 59.2 | |||
$2.000 | $6.000 | 58.8 | |||
$0.440 | $2.200 | 58.7 | |||
$0.440 | $2.200 | 58.1 | |||
$0.780 | $3.900 | 57.4 | |||
$0.075 | $0.200 | 55.9 | |||
$0.600 | $1.920 | 55.9 | |||
$0.600 | $1.920 | 55.9 | |||
$0.375 | $2.250 | 55.7 | |||
$0.080 | $0.160 | 53.9 | |||
$0.300 | $2.500 | 53.0 | |||
$0.300 | $2.500 | 53.0 | |||
$0.064 | $0.224 | 52.1 | |||
$0.064 | $0.224 | 52.1 | |||
$0.800 | $3.200 | 50.1 | |||
$0.120 | $0.500 | 49.0 | |||
$0.120 | $0.500 | 49.0 | |||
$0.014 | $0.028 | 48.2 | |||
$0.060 | $0.240 | 45.7 | |||
$0.100 | $0.625 | 42.4 | |||
$0.100 | $0.300 | 42.3 | |||
$0.070 | $0.140 | 39.7 | |||
$2.500 | $10.000 | 37.9 | |||
$0.100 | $0.400 | 34.1 | |||
$0.100 | $0.400 | 34.1 | |||
$0.200 | $0.600 | 31.3 | |||
$0.390 | $0.900 | 21.8 | |||
$0.320 | $1.400 | 16.1 | |||
$0.320 | $1.400 | 16.1 | |||
$0.260 | $1.560 | 13.1 | |||
$0.270 | $1.000 | - | |||
$0.270 | $1.000 | - | |||
$0.750 | $3.750 | - |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
Multimodal Understanding benchmark testing vision-language models on expert-level tasks.
This leaderboard shows all models with MMMU 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.