Science coding benchmark measuring AI ability to solve scientific computing tasks.
Data from Artificial Analysis
As of November 21, 2026, the top-scoring model on SciCode is Claude Fable 5.1 at 63.1%, followed by Gemini 4 Argon at 61.8% and Claude Fable 5 at 61.0%. 108 models have been evaluated on this benchmark.
Last updated: November 21, 2026
Models
108
Best Score
63.1
Average
45.1
Std Dev
11.0
Provider | Model | Input $/M | Output $/M | SciCode | Actions |
|---|---|---|---|---|---|
$10.000 | $50.000 | 63.1 | |||
$2.000 | $10.000 | 61.8 | |||
$10.000 | $50.000 | 61.0 | |||
$2.000 | $10.000 | 61.0 | |||
$0.326 | $0.652 | 60.9 | |||
$0.240 | $6.000 | 60.8 | |||
$0.180 | $9.500 | 59.5 | |||
$0.070 | $1.400 | 59.0 | |||
$1.250 | $4.250 | 58.8 | |||
$1.000 | $6.000 | 58.7 | |||
$1.250 | $4.250 | 58.4 | |||
$0.100 | $0.200 | 57.4 | |||
$2.000 | $6.000 | 57.4 | |||
$0.750 | $3.750 | 57.2 | |||
$2.000 | $10.000 | 57.1 | |||
$0.750 | $3.750 | 56.6 | |||
$2.000 | $6.000 | 56.5 | |||
$5.000 | $25.000 | 56.5 | |||
$5.000 | $25.000 | 56.4 | |||
$5.000 | $30.000 | 56.1 | |||
$1.000 | $5.000 | 55.1 | |||
$2.000 | $6.000 | 55.0 | |||
$2.000 | $12.000 | 55.0 | |||
$0.100 | $0.500 | 55.0 | |||
$5.000 | $25.000 | 54.4 | |||
$2.000 | $10.000 | 54.3 | |||
$0.700 | $2.100 | 54.2 | |||
$0.900 | $0.900 | 54.1 | |||
$1.500 | $9.000 | 53.9 | |||
$0.200 | $1.200 | 53.6 | |||
$0.750 | $3.750 | 53.4 | |||
$0.135 | $0.400 | 53.4 | |||
$2.000 | $6.000 | 53.2 | |||
$0.375 | $2.250 | 52.1 | |||
$0.040 | $0.100 | 51.9 | |||
$0.040 | $0.078 | 51.6 | |||
$0.000 | $0.000 | 51.5 | |||
$0.100 | $0.224 | 51.3 | |||
$0.007 | $0.950 | 51.2 | |||
$0.111 | $1.322 | 51.0 | |||
$0.480 | $1.800 | 50.6 | |||
$0.014 | $0.029 | 50.3 | |||
$3.000 | $15.000 | 50.1 | |||
$0.000 | $0.000 | 50.1 | |||
$0.450 | $1.200 | 49.7 | |||
$0.216 | $0.647 | 49.7 | |||
$1.475 | $4.425 | 49.5 | |||
$0.132 | $0.528 | 48.6 | |||
$0.150 | $0.600 | 48.0 | |||
$0.600 | $3.000 | 47.8 | |||
$0.050 | $0.200 | 47.6 | |||
$0.100 | $0.625 | 47.2 | |||
$0.230 | $0.960 | 47.1 | |||
$1.000 | $4.050 | 47.0 | |||
$0.035 | $0.900 | 46.6 | |||
$1.000 | $10.000 | 46.3 | |||
$0.320 | $1.280 | 46.1 | |||
$3.000 | $15.000 | 45.7 | |||
$0.100 | $0.100 | 45.5 | |||
$0.390 | $0.900 | 44.8 | |||
$0.899 | $2.825 | 44.8 | |||
$0.060 | $0.180 | 44.2 | |||
$0.200 | $1.150 | 43.9 | |||
$0.250 | $1.500 | 43.4 | |||
$0.250 | $1.000 | 43.3 | |||
$1.100 | $4.400 | 42.8 | |||
$0.250 | $0.900 | 42.8 | |||
$0.042 | $0.123 | 42.4 | |||
$1.000 | $5.000 | 42.2 | |||
$0.021 | $0.063 | 42.0 | |||
$0.450 | $0.900 | 41.4 | |||
$0.300 | $2.500 | 41.3 | |||
$0.400 | $1.760 | 40.3 | |||
$1.500 | $7.500 | 40.2 | |||
$0.050 | $0.190 | 40.0 | |||
$0.260 | $0.900 | 39.7 | |||
$0.250 | $1.000 | 39.0 | |||
$0.125 | $1.000 | 39.0 | |||
$0.017 | $0.085 | 38.9 | |||
$0.040 | $0.150 | 38.5 | |||
$0.300 | $1.500 | 38.5 | |||
$0.550 | $2.190 | 38.3 | |||
$0.270 | $1.000 | 38.0 | |||
$0.250 | $0.750 | 37.7 | |||
$0.050 | $0.700 | 36.6 | |||
$0.300 | $1.200 | 36.3 | |||
$0.120 | $0.800 | 36.2 | |||
$0.064 | $0.224 | 36.0 | |||
$0.030 | $0.100 | 34.0 | |||
$0.200 | $0.900 | 33.0 | |||
$0.400 | $0.900 | 32.8 | |||
$0.440 | $2.200 | 32.4 | |||
$0.020 | $0.096 | 32.1 | |||
$0.200 | $0.600 | 31.7 | |||
$0.060 | $0.150 | 31.5 | |||
$0.080 | $0.200 | 30.7 | |||
$0.060 | $0.240 | 30.6 | |||
$0.080 | $0.120 | 29.5 | |||
$0.075 | $0.200 | 28.6 | |||
$0.200 | $0.200 | 27.9 | |||
$0.100 | $0.300 | 27.8 | |||
$0.150 | $0.600 | 25.5 | |||
$0.200 | $0.200 | 23.8 | |||
$0.080 | $0.160 | 23.3 | |||
$0.100 | $0.300 | 21.3 | |||
$0.150 | $0.150 | 20.7 | |||
$0.050 | $0.150 | 16.4 | |||
$0.350 | $0.500 | 14.4 |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
Science coding benchmark measuring AI ability to solve scientific computing tasks.
This leaderboard shows all models with SciCode 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.