AGIEval English Leaderboard
AGIEval English — human-level reasoning tasks from standardized exams like SAT, LSAT, and civil service exams.
Data from LayerLens
Models
97
Best Score
94.0
Average
77.5
Std Dev
12.4
Provider | Model | Input $/M | Output $/M | AGIEval English | Actions |
|---|---|---|---|---|---|
$2.000 | $12.000 | 94.0 | |||
$2.000 | $12.000 | 93.2 | |||
$0.550 | $3.500 | 91.4 | |||
$1.250 | $10.000 | 91.4 | |||
$1.250 | $10.000 | 91.1 | |||
$2.000 | $8.000 | 90.9 | |||
$0.300 | $2.400 | 90.6 | |||
$0.400 | $3.200 | 90.3 | |||
$0.300 | $1.400 | 90.1 | |||
$0.300 | $1.400 | 90.1 | |||
$3.000 | $15.000 | 89.5 | |||
$0.100 | $0.400 | 89.5 | |||
$0.250 | $1.000 | 89.5 | |||
$3.000 | $15.000 | 89.3 | |||
$0.450 | $2.150 | 89.0 | |||
$0.270 | $0.410 | 89.0 | |||
$0.200 | $0.500 | 88.9 | |||
$0.200 | $0.500 | 88.6 | |||
$0.350 | $1.710 | 88.6 | |||
$0.350 | $1.710 | 88.6 | |||
$0.150 | $0.400 | 88.0 | |||
$1.100 | $4.400 | 87.8 | |||
$0.700 | $2.500 | 87.6 | |||
$3.000 | $15.000 | 87.5 | |||
$0.250 | $2.000 | 87.1 | |||
$0.200 | $1.100 | 86.4 | |||
$3.000 | $15.000 | 86.0 | |||
$3.000 | $15.000 | 85.7 | |||
$0.270 | $0.410 | 85.7 | |||
$0.300 | $0.500 | 85.2 | |||
$0.255 | $1.000 | 85.1 | |||
$0.090 | $0.450 | 84.8 | |||
$0.210 | $0.790 | 84.7 | |||
$0.210 | $0.790 | 84.7 | |||
$0.500 | $3.000 | 84.2 | |||
$0.500 | $3.000 | 84.2 | |||
$3.000 | $15.000 | 83.9 | |||
$3.000 | $15.000 | 83.9 | |||
$15.000 | $75.000 | 83.4 | |||
$15.000 | $75.000 | 83.4 | |||
$0.080 | $0.280 | 83.1 | |||
$0.080 | $0.280 | 83.1 | |||
$0.550 | $2.200 | 83.0 | |||
$0.039 | $0.190 | 82.7 | |||
$15.000 | $75.000 | 82.0 | |||
$15.000 | $75.000 | 82.0 | |||
$1.100 | $4.400 | 81.9 | |||
$0.400 | $2.200 | 81.5 | |||
$0.550 | $2.000 | 80.9 | |||
$0.200 | $0.880 | 80.7 | |||
$0.400 | $2.000 | 80.7 | |||
$0.150 | $0.750 | 79.8 | |||
$0.150 | $0.750 | 79.8 | |||
$0.030 | $0.140 | 79.6 | |||
$1.200 | $6.000 | 79.1 | |||
$0.400 | $2.400 | 77.8 | |||
$1.000 | $5.000 | 76.9 | |||
$1.000 | $5.000 | 76.9 | |||
$0.150 | $0.600 | 76.7 | |||
$0.071 | $0.100 | 76.7 | |||
$0.320 | $0.890 | 76.2 | |||
$0.300 | $2.500 | 74.2 | |||
$0.300 | $2.500 | 74.2 | |||
$0.280 | $1.100 | 74.1 | |||
$3.000 | $15.000 | 74.0 | |||
$0.500 | $1.500 | 74.0 | |||
$0.100 | $0.400 | 73.4 | |||
$0.400 | $2.000 | 71.9 | |||
$1.750 | $14.000 | 71.7 | |||
$3.000 | $15.000 | 71.3 | |||
$3.000 | $15.000 | 71.2 | |||
$0.400 | $2.000 | 70.3 | |||
$2.500 | $10.000 | 70.1 | |||
$2.000 | $8.000 | 70.0 | |||
$1.250 | $10.000 | 69.4 | |||
$2.500 | $10.000 | 68.5 | |||
$0.060 | $0.140 | 68.2 | |||
$0.200 | $0.500 | 67.4 | |||
$0.200 | $0.500 | 67.0 | |||
$0.130 | $0.850 | 66.4 | |||
$0.800 | $4.000 | 66.2 | |||
$0.060 | $0.240 | 65.8 | |||
$0.800 | $3.200 | 65.5 | |||
$0.040 | $0.150 | 65.1 | |||
$2.000 | $6.000 | 64.7 | |||
$2.000 | $6.000 | 64.5 | |||
$4.000 | $4.000 | 63.7 | |||
$0.300 | $0.300 | 62.5 | |||
$0.060 | $0.180 | 62.3 | |||
$2.500 | $10.000 | 60.4 | |||
$0.100 | $0.300 | 60.0 | |||
$0.100 | $0.400 | 58.0 | |||
$0.100 | $0.400 | 58.0 | |||
$0.035 | $0.140 | 55.6 | |||
$0.020 | $0.040 | 53.1 | |||
$0.080 | $0.300 | 27.4 | |||
$0.051 | $0.340 | 26.5 |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
Deploy OpenClaw in Under 1 Minute— We handle hosting, scaling, and maintenance
93 out of our 301 tracked models have had a price change in March.
Get our weekly newsletter on pricing changes, new releases, and tools.
About AGIEval English
AGIEval English — human-level reasoning tasks from standardized exams like SAT, LSAT, and civil service exams.
This leaderboard shows all models with AGIEval English benchmark scores, ranked from highest to lowest. Pricing data is included to help you compare performance against cost.
Other Benchmark Leaderboards
Built by @aellman
Tools
Directories
Models & Pricing
Rankings
- All Rankings
- All Benchmarks
- Best LLM for Coding
- Best LLM for Math
- Best LLM for Writing
- Best LLM for RAG
- Best LLM for OpenClaw
- Best LLM for Cursor
- Best LLM for Windsurf
- Best LLM for Cline
- Best LLM for Aider
- Best LLM for GitHub Copilot
- Best LLM for Bolt
- Best LLM for Continue.dev
- MMLU-Pro
- GPQA
- LiveCodeBench
- Aider
- AIME
- MATH (Hard)
- Big-Bench Hard
2026 68 Ventures, LLC. All rights reserved.