Tau2 benchmark testing multi-turn agent capabilities in airline and retail domains.
Data from Artificial Analysis
As of June 2, 2026, the top-scoring model on Tau2 is GLM-4.7-Flash at 98.8%, followed by GLM-5 Turbo at 98.5% and GLM-5V Turbo at 98.5%. 251 models have been evaluated on this benchmark.
Last updated: June 2, 2026
Models
251
Best Score
98.8
Average
51.0
Std Dev
30.7
Provider | Model | Input $/M | Output $/M | Tau2 | Actions |
|---|---|---|---|---|---|
$0.060 | $0.400 | 98.8 | |||
$1.200 | $4.000 | 98.5 | |||
$1.200 | $4.000 | 98.5 | |||
$0.600 | $2.080 | 98.3 | |||
$0.980 | $3.080 | 97.7 | |||
$0.600 | $2.080 | 97.4 | |||
$0.980 | $3.080 | 97.1 | |||
$0.435 | $0.870 | 96.2 | |||
$0.400 | $1.540 | 95.9 | |||
$0.400 | $1.900 | 95.9 | |||
$0.684 | $3.400 | 95.9 | |||
$0.390 | $0.900 | 95.6 | |||
$2.000 | $12.000 | 95.6 | |||
$1.500 | $9.000 | 95.6 | |||
$0.150 | $1.150 | 95.3 | |||
$0.140 | $0.900 | 95.3 | |||
$1.500 | $9.000 | 95.3 | |||
$0.100 | $0.300 | 95.0 | |||
$0.098 | $0.197 | 95.0 | |||
$1.250 | $3.750 | 94.7 | |||
$0.090 | $0.300 | 94.4 | |||
$0.098 | $0.197 | 94.4 | |||
$0.400 | $1.540 | 94.2 | |||
$0.435 | $0.870 | 94.2 | |||
$0.195 | $0.900 | 93.9 | |||
$0.684 | $3.400 | 93.9 | |||
$0.260 | $0.900 | 93.6 | |||
$0.000 | $0.000 | 93.3 | |||
$0.100 | $0.300 | 93.3 | |||
$0.550 | $2.200 | 93.0 | |||
$1.750 | $14.000 | 92.1 | |||
$5.000 | $25.000 | 92.1 | |||
$0.060 | $0.400 | 91.8 | |||
$0.400 | $2.000 | 91.2 | |||
$0.435 | $0.870 | 91.2 | |||
$0.229 | $0.343 | 90.6 | |||
$0.250 | $0.500 | 90.3 | |||
$5.000 | $25.000 | 89.5 | |||
$0.140 | $0.900 | 89.2 | |||
$0.207 | $0.828 | 88.6 | |||
$5.000 | $25.000 | 88.6 | |||
$0.090 | $0.300 | 87.4 | |||
$2.000 | $12.000 | 87.1 | |||
$0.195 | $0.900 | 87.1 | |||
$2.500 | $15.000 | 87.1 | |||
$1.250 | $10.000 | 86.8 | |||
$0.255 | $1.000 | 86.8 | |||
$0.040 | $0.150 | 86.8 | |||
$1.250 | $10.000 | 86.6 | |||
$5.000 | $25.000 | 86.3 | |||
$0.140 | $0.900 | 86.3 | |||
$1.750 | $14.000 | 86.0 | |||
$0.010 | $0.030 | 86.0 | |||
$0.290 | $0.950 | 85.4 | |||
$0.040 | $0.150 | 85.1 | |||
$0.140 | $0.900 | 85.1 | |||
$1.250 | $10.000 | 84.8 | |||
$10.500 | $84.000 | 84.8 | |||
$5.000 | $25.000 | 84.8 | |||
$0.279 | $1.200 | 84.8 | |||
$0.260 | $0.900 | 84.5 | |||
$1.250 | $10.000 | 84.2 | |||
$0.100 | $0.300 | 83.9 | |||
$0.390 | $0.900 | 83.9 | |||
$0.780 | $3.900 | 83.6 | |||
$0.780 | $3.900 | 83.6 | |||
$1.250 | $10.000 | 83.0 | |||
$1.250 | $10.000 | 81.9 | |||
$0.400 | $1.900 | 81.3 | |||
$2.000 | $8.000 | 80.7 | |||
$0.500 | $3.000 | 80.4 | |||
$0.110 | $0.800 | 79.5 | |||
$3.000 | $15.000 | 79.5 | |||
$0.229 | $0.343 | 79.0 | |||
$3.000 | $15.000 | 79.0 | |||
$3.000 | $15.000 | 78.1 | |||
$0.430 | $1.740 | 76.9 | |||
$0.200 | $1.500 | 75.7 | |||
$3.000 | $15.000 | 75.7 | |||
$3.000 | $15.000 | 74.9 | |||
$2.500 | $15.000 | 74.6 | |||
$0.780 | $3.900 | 74.3 | |||
$1.750 | $14.000 | 74.3 | |||
$5.000 | $25.000 | 74.0 | |||
$15.000 | $75.000 | 73.4 | |||
$0.600 | $2.500 | 73.4 | |||
$0.435 | $0.870 | 72.5 | |||
$15.000 | $75.000 | 71.4 | |||
$0.250 | $2.000 | 71.0 | |||
$0.250 | $0.750 | 70.8 | |||
$3.000 | $15.000 | 70.5 | |||
$0.430 | $1.740 | 70.5 | |||
$0.250 | $2.000 | 68.4 | |||
$2.000 | $12.000 | 68.1 | |||
$1.250 | $10.000 | 67.0 | |||
$0.039 | $0.100 | 65.8 | |||
$0.200 | $0.500 | 65.8 | |||
$3.000 | $15.000 | 64.6 | |||
$0.200 | $0.500 | 63.7 | |||
$0.000 | $0.000 | 63.7 | |||
$0.250 | $2.000 | 62.9 | |||
$15.000 | $60.000 | 62.6 | |||
$0.300 | $2.500 | 62.0 | |||
$0.550 | $2.200 | 61.1 | |||
$0.029 | $0.140 | 60.2 | |||
$0.120 | $0.370 | 59.9 | |||
$1.500 | $9.000 | 58.8 | |||
$0.550 | $2.200 | 55.6 | |||
$3.000 | $15.000 | 54.7 | |||
$1.000 | $5.000 | 54.7 | |||
$1.000 | $10.000 | 54.1 | |||
$0.260 | $0.900 | 54.1 | |||
$0.100 | $0.100 | 53.2 | |||
$0.400 | $1.600 | 52.9 | |||
$3.000 | $15.000 | 52.3 | |||
$0.029 | $0.140 | 50.3 | |||
$3.000 | $15.000 | 50.0 | |||
$3.000 | $15.000 | 48.8 | |||
$0.200 | $0.770 | 47.1 | |||
$2.000 | $8.000 | 47.1 | |||
$0.125 | $0.850 | 46.5 | |||
$1.250 | $10.000 | 46.5 | |||
$1.750 | $14.000 | 46.5 | |||
$0.104 | $0.416 | 45.6 | |||
$0.039 | $0.100 | 45.0 | |||
$0.220 | $0.900 | 43.6 | |||
$0.060 | $0.300 | 43.6 | |||
$0.500 | $3.000 | 43.3 | |||
$0.600 | $2.200 | 43.0 | |||
$0.098 | $0.300 | 41.5 | |||
$0.050 | $0.200 | 40.9 | |||
$0.400 | $2.000 | 40.6 | |||
$0.060 | $0.300 | 40.4 | |||
$2.500 | $12.500 | 38.3 | |||
$0.210 | $0.790 | 37.4 | |||
$0.270 | $0.950 | 37.1 | |||
$0.270 | $0.950 | 37.1 | |||
$2.000 | $6.000 | 36.5 | |||
$0.500 | $2.150 | 36.5 | |||
$0.050 | $0.400 | 36.5 | |||
$0.200 | $0.880 | 35.1 | |||
$2.500 | $15.000 | 35.1 | |||
$0.210 | $0.790 | 34.8 | |||
$0.360 | $0.400 | 34.5 | |||
$0.080 | $0.200 | 34.5 | |||
$0.070 | $0.270 | 34.5 | |||
$0.400 | $2.200 | 34.2 | |||
$0.270 | $0.410 | 33.9 | |||
$0.270 | $0.410 | 33.9 | |||
$0.071 | $0.100 | 33.3 | |||
$2.000 | $6.000 | 33.0 | |||
$0.780 | $3.900 | 32.8 | |||
$1.000 | $5.000 | 32.5 | |||
$0.080 | $0.200 | 32.2 | |||
$0.300 | $2.500 | 31.6 | |||
$0.400 | $2.200 | 31.6 | |||
$0.300 | $0.900 | 31.6 | |||
$1.100 | $4.400 | 31.3 | |||
$0.250 | $1.500 | 31.3 | |||
$2.000 | $6.000 | 30.7 | |||
$0.100 | $0.400 | 30.7 | |||
$0.300 | $0.900 | 30.7 | |||
$0.050 | $0.400 | 30.4 | |||
$0.100 | $0.400 | 30.4 | |||
$0.080 | $0.280 | 29.8 | |||
$0.100 | $0.400 | 29.5 | |||
$0.075 | $0.200 | 29.5 | |||
$0.080 | $0.200 | 29.2 | |||
$0.104 | $0.416 | 29.2 | |||
$0.550 | $2.200 | 28.6 | |||
$0.070 | $0.280 | 28.4 | |||
$0.080 | $0.400 | 28.1 | |||
$0.100 | $0.400 | 28.1 | |||
$0.050 | $0.200 | 27.8 | |||
$0.455 | $0.900 | 27.2 | |||
$0.200 | $0.200 | 27.2 | |||
$0.100 | $0.400 | 26.9 | |||
$0.100 | $0.320 | 26.6 | |||
$0.200 | $0.200 | 26.6 | |||
$1.000 | $3.000 | 26.6 | |||
$0.200 | $1.100 | 26.6 | |||
$0.150 | $0.150 | 26.6 | |||
$0.080 | $0.280 | 26.0 | |||
$0.050 | $0.400 | 25.7 | |||
$0.200 | $0.200 | 25.4 | |||
$0.050 | $0.200 | 25.4 | |||
$0.100 | $0.300 | 25.1 | |||
$0.100 | $0.400 | 25.1 | |||
$0.050 | $0.200 | 24.9 | |||
$0.400 | $0.900 | 24.9 | |||
$0.800 | $4.000 | 24.6 | |||
$0.400 | $2.000 | 24.3 | |||
$0.455 | $0.900 | 24.0 | |||
$0.040 | $0.160 | 23.4 | |||
$0.900 | $0.900 | 23.1 | |||
$0.200 | $0.770 | 22.8 | |||
$0.600 | $1.800 | 22.5 | |||
$0.130 | $0.400 | 22.5 | |||
$0.117 | $1.365 | 22.5 | |||
$0.080 | $0.280 | 22.2 | |||
$1.000 | $3.000 | 22.2 | |||
$0.700 | $0.800 | 21.9 | |||
$0.040 | $0.160 | 21.9 | |||
$0.130 | $0.400 | 21.6 | |||
$0.090 | $0.780 | 21.6 | |||
$0.200 | $0.200 | 21.3 | |||
$0.200 | $0.600 | 21.3 | |||
$0.250 | $1.250 | 21.1 | |||
$0.030 | $0.050 | 21.1 | |||
$0.400 | $2.000 | 19.9 | |||
$0.130 | $0.900 | 19.9 | |||
$0.050 | $0.080 | 19.6 | |||
$0.600 | $1.800 | 19.6 | |||
$0.200 | $0.200 | 19.3 | |||
$0.900 | $0.900 | 19.0 | |||
$0.200 | $0.200 | 19.0 | |||
$0.100 | $0.400 | 19.0 | |||
$0.130 | $0.520 | 19.0 | |||
$0.100 | $0.400 | 18.4 | |||
$0.150 | $0.600 | 17.8 | |||
$0.060 | $0.240 | 17.5 | |||
$0.100 | $0.400 | 17.3 | |||
$0.020 | $0.050 | 16.4 | |||
$0.080 | $0.300 | 15.5 | |||
$0.340 | $0.390 | 15.2 | |||
$2.500 | $10.000 | 15.2 | |||
$0.300 | $2.500 | 14.9 | |||
$0.060 | $0.060 | 14.6 | |||
$0.800 | $3.200 | 14.0 | |||
$0.035 | $0.140 | 14.0 | |||
$2.000 | $8.000 | 13.5 | |||
$0.100 | $0.200 | 12.6 | |||
$0.550 | $2.000 | 11.4 | |||
$0.040 | $0.130 | 10.8 | |||
$0.080 | $0.160 | 10.5 | |||
$0.010 | $0.020 | 10.5 | |||
$0.043 | $0.172 | 10.2 | |||
$0.040 | $0.080 | 5.0 | |||
$0.060 | $0.120 | 5.0 | |||
$0.510 | $0.740 | - | |||
$0.040 | $0.040 | - | |||
$0.020 | $0.020 | - | |||
$0.065 | $0.140 | - | |||
$0.050 | $0.200 | - | |||
$0.900 | $0.900 | - | |||
$1.250 | $10.000 | - | |||
$0.120 | $0.200 | - | |||
$0.150 | $0.500 | - | |||
$0.270 | $0.400 | - | |||
$0.150 | $0.500 | - | |||
$0.200 | $0.200 | - |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
Get our weekly newsletter on pricing changes, new releases, and tools.
Tau2 benchmark testing multi-turn agent capabilities in airline and retail domains.
This leaderboard shows all models with Tau2 benchmark scores, ranked from highest to lowest. Pricing data is included to help you compare performance against cost.
Built by @aellman
2026 68 Ventures, LLC. All rights reserved.