Big-Bench Hard — challenging subset of BIG-Bench focusing on tasks where language models previously underperformed.
Data from LayerLens
As of November 21, 2026, the top-scoring model on BBH is Gemini 3.1 Pro Preview at 96.1%, followed by Qwen3.7 Max at 95.8% and Qwen3.8 Max at 95.5%. 145 models have been evaluated on this benchmark.
Last updated: November 21, 2026
Models
145
Best Score
96.1
Average
78.9
Std Dev
19.3
Provider | Model | Input $/M | Output $/M | BBH | Actions |
|---|---|---|---|---|---|
$1.000 | $6.000 | 96.1 | |||
$1.475 | $4.425 | 95.8 | |||
$2.000 | $6.000 | 95.5 | |||
$1.027 | $6.162 | 95.2 | |||
$5.000 | $25.000 | 94.6 | |||
$3.000 | $15.000 | 94.4 | |||
$3.000 | $15.000 | 94.3 | |||
$0.600 | $1.920 | 94.3 | |||
$0.600 | $1.920 | 94.3 | |||
$5.000 | $25.000 | 94.1 | |||
$5.000 | $30.000 | 94.1 | |||
$0.320 | $1.280 | 94.0 | |||
$0.750 | $3.750 | 94.0 | |||
$0.250 | $0.900 | 93.5 | |||
$0.899 | $2.825 | 93.3 | |||
$2.000 | $6.000 | 93.3 | |||
$0.500 | $3.000 | 93.1 | |||
$0.750 | $3.750 | 92.7 | |||
$0.260 | $0.900 | 92.7 | |||
$0.780 | $3.900 | 92.6 | |||
$0.500 | $3.000 | 92.4 | |||
$0.195 | $0.900 | 92.4 | |||
$2.000 | $10.000 | 92.4 | |||
$0.400 | $1.760 | 92.1 | |||
$0.040 | $0.078 | 92.0 | |||
$0.490 | $2.500 | 91.9 | |||
$0.490 | $2.500 | 91.9 | |||
$5.000 | $25.000 | 91.8 | |||
$5.000 | $25.000 | 91.8 | |||
$0.100 | $0.100 | 91.8 | |||
$1.500 | $9.000 | 91.7 | |||
$0.188 | $1.125 | 91.6 | |||
$0.007 | $0.950 | 91.6 | |||
$1.200 | $4.000 | 91.5 | |||
$0.030 | $0.130 | 91.5 | |||
$0.050 | $0.700 | 91.3 | |||
$0.000 | $0.000 | 91.2 | |||
$5.000 | $25.000 | 91.1 | |||
$1.000 | $4.050 | 91.1 | |||
$1.250 | $10.000 | 90.9 | |||
$0.065 | $0.750 | 90.8 | |||
$0.065 | $0.260 | 90.6 | |||
$0.600 | $3.000 | 90.6 | |||
$0.260 | $1.560 | 90.6 | |||
$3.000 | $15.000 | 90.3 | |||
$0.050 | $0.190 | 90.2 | |||
$0.450 | $0.900 | 90.2 | |||
$0.000 | $0.000 | 90.1 | |||
$0.200 | $1.200 | 89.7 | |||
$2.000 | $8.000 | 89.6 | |||
$0.120 | $0.500 | 89.5 | |||
$0.120 | $0.500 | 89.5 | |||
$0.390 | $0.900 | 89.4 | |||
$1.000 | $10.000 | 88.7 | |||
$0.200 | $0.880 | 88.7 | |||
$0.300 | $0.900 | 88.6 | |||
$0.450 | $1.200 | 88.6 | |||
$0.209 | $0.310 | 88.5 | |||
$0.300 | $0.900 | 88.5 | |||
$0.320 | $1.400 | 88.4 | |||
$0.320 | $1.400 | 88.4 | |||
$0.209 | $0.310 | 88.2 | |||
$0.270 | $0.410 | 88.0 | |||
$0.500 | $2.150 | 87.9 | |||
$0.125 | $1.000 | 87.7 | |||
$0.250 | $1.500 | 87.7 | |||
$0.216 | $0.647 | 87.6 | |||
$0.200 | $0.900 | 87.5 | |||
$0.550 | $2.200 | 87.1 | |||
$0.230 | $0.960 | 87.1 | |||
$0.600 | $2.200 | 87.0 | |||
$0.650 | $3.250 | 87.0 | |||
$0.025 | $0.200 | 86.9 | |||
$0.600 | $2.500 | 86.7 | |||
$0.300 | $2.500 | 86.2 | |||
$0.064 | $0.224 | 85.8 | |||
$0.064 | $0.224 | 85.8 | |||
$0.430 | $1.750 | 85.5 | |||
$0.430 | $1.750 | 85.5 | |||
$0.600 | $2.500 | 85.4 | |||
$0.270 | $0.950 | 85.4 | |||
$0.080 | $0.200 | 84.6 | |||
$0.080 | $0.200 | 84.6 | |||
$0.017 | $0.085 | 84.4 | |||
$0.030 | $0.100 | 84.3 | |||
$0.900 | $0.900 | 84.2 | |||
$0.900 | $0.900 | 84.2 | |||
$0.800 | $3.200 | 83.9 | |||
$0.090 | $0.900 | 82.3 | |||
$0.130 | $0.850 | 82.2 | |||
$1.500 | $7.500 | 82.0 | |||
$1.000 | $5.000 | 82.0 | |||
$1.000 | $5.000 | 82.0 | |||
$0.000 | $0.000 | 81.9 | |||
$0.200 | $0.600 | 81.8 | |||
$0.060 | $0.240 | 81.8 | |||
$0.060 | $0.240 | 81.8 | |||
$0.440 | $2.200 | 81.5 | |||
$0.500 | $1.500 | 81.3 | |||
$0.440 | $2.200 | 80.5 | |||
$0.020 | $0.096 | 80.1 | |||
$0.250 | $0.950 | 79.7 | |||
$0.250 | $0.950 | 79.7 | |||
$2.500 | $10.000 | 79.6 | |||
$0.100 | $0.300 | 79.3 | |||
$2.500 | $10.000 | 76.7 | |||
$0.080 | $0.160 | 76.6 | |||
$0.075 | $0.200 | 76.5 | |||
$1.250 | $7.500 | 75.3 | |||
$0.075 | $0.400 | 75.2 | |||
$0.000 | $0.000 | 74.3 | |||
$0.288 | $0.320 | 72.4 | |||
$0.070 | $0.280 | 71.9 | |||
$0.014 | $0.028 | 69.8 | |||
$0.625 | $5.000 | 69.8 | |||
$1.750 | $14.000 | 67.6 | |||
$1.000 | $3.000 | 67.2 | |||
$1.000 | $3.000 | 67.2 | |||
$0.000 | $0.000 | 64.2 | |||
$0.300 | $0.900 | 62.9 | |||
$0.300 | $2.500 | 61.6 | |||
$0.300 | $2.500 | 61.6 | |||
$0.035 | $0.140 | 61.5 | |||
$0.270 | $1.000 | 60.5 | |||
$0.270 | $1.000 | 60.5 | |||
$0.060 | $0.240 | 59.0 | |||
$0.375 | $2.250 | 58.0 | |||
$0.100 | $0.320 | 56.6 | |||
$0.100 | $0.400 | 56.0 | |||
$0.100 | $0.400 | 56.0 | |||
$0.340 | $0.390 | 55.9 | |||
$0.270 | $0.410 | 52.8 | |||
$0.020 | $0.040 | 46.1 | |||
$0.100 | $0.625 | 45.6 | |||
$0.100 | $0.280 | 43.8 | |||
$2.000 | $6.000 | 41.2 | |||
$0.030 | $0.050 | 36.0 | |||
$0.750 | $0.800 | 35.8 | |||
$0.070 | $0.140 | 34.5 | |||
$0.200 | $0.200 | 28.7 | |||
$0.040 | $0.040 | 18.4 | |||
$0.300 | $0.300 | 17.1 | |||
$0.660 | $0.800 | 11.4 | |||
$0.020 | $0.020 | 8.7 | |||
$0.900 | $0.900 | 2.9 |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
Big-Bench Hard — challenging subset of BIG-Bench focusing on tasks where language models previously underperformed.
This leaderboard shows all models with BBH 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.