Best for Coding
Coding benchmarks54
BenchmarkByLeaderModels
Coding11
Agents11
Code review1
Reported by labs23
Legacy · saturated or no longer reported8
No benchmark matches
| Model | Terminal-Bench Science 0.1 | Per task | Price | Speed | Supports | Context |
|---|---|---|---|---|---|---|
63.3max | $3.26 | $10 / $50 | 69 | 1.05M | ||
61.9xhigh | $3.46 | $4 / $20 | 84 | 1M | ||
58.1max | $0.72 | $2 / $10 | 52 | 1.05M | ||
53.3max | $5.46 | $2 / $10 | 137 | 1M | ||
52.9high | $1.99 | $2 / $10 | 84 | 1M | ||
43.3max | $7.63 | $10 / $50 | 69 | 1M | ||
30max | $1.04 | $2 / $10 | 128 | 1.05M | ||
28.6max | $5.86 | $5 / $25 | 55 | 1M | ||
22.4max | $1.99 | $4 / $20 | 114 | 1.05M | ||
20max | $0.21 | $0.10 / $0.50 | 234 | 1M | ||
13.8max | $1.40 | $2 / $12 | 142 | 1.05M | ||
11.9thinking | $5.41 | $2 / $6 | 40 | 984K | ||
11max | $1.60 | $1.25 / $4.25 | 128 | 1M | ||
10high | $1.24 | $0.75 / $3.75 | 149 | 1M | ||
9.5high | $2.73 | $2 / $6 | 87 | 500K | ||
9.5max | $2.01 | $1.40 / $4.40 | 186 | 1M | ||
8.6max | $0.068 | $0.10 / $0.50 | 138 | 1.05M | ||
6.2high | $1.48 | $2 / $6 | 65 | 500K | ||
5.7max | $0.67 | $1.32 / $3.96 | 90 | 1M | ||
5.7thinking | $0.13 | $0.43 / $0.87 | 54 | 1M | ||
4.8max | $0.28 | $0.15 / $0.50 | 179 | 1M | ||
4.3thinking | $0.062 | $0.14 / $0.28 | 41 | 1M | ||
3.3max | $0.18 | $0.20 / $1.20 | 178 | 1.05M | ||
2.4thinking | $1.03 | $1 / $2.70 | 93 | 1M | ||
1medium | $1.13 | $0.42 / $2.55 | 50 | 262K | ||
0.5thinking | $0.51 | $0.30 / $1.20 | 157 | 524K | ||
0high | $0.19 | $0.30 / $2.50 | 454 | 1M | ||
0high | $0.058 | $0.30 / $1.10 | 141 | 131K | ||
0thinking | $0.58 | $0.50 / $2.50 | 138 | 1M | ||
0 | $0.19 | $0.10 / $0.40 | 413 | 1M | ||
0xhigh | — | $0.95 / $4.05 | 190 | 256K | ||
0thinking | $0.089 | $0.45 / $1.20 | 219 | 256K | ||
0 | — | $1 / $4 | 1,109 | 524K |
