AIME 2024 Leaderboard
American Invitational Mathematics Examination 2024 problems testing olympiad-level mathematical reasoning.
Data from Artificial Analysis
As of April 4, 2026, the top-scoring model on AIME 2024 is GPT-5 at 95.7%, followed by Grok 4 at 94.3% and o4 Mini at 94.0%. 118 models have been evaluated on this benchmark.
Last updated: April 4, 2026
Models
118
Best Score
95.7
Average
40.4
Std Dev
30.8
Provider | Model | Input $/M | Output $/M | AIME 2024 | Actions |
|---|---|---|---|---|---|
$0.625 | $5.000 | 95.7 | |||
$3.000 | $15.000 | 94.3 | |||
$0.550 | $2.200 | 94.0 | |||
$0.149 | $0.900 | 94.0 | |||
$0.250 | $0.500 | 93.3 | |||
$0.625 | $5.000 | 91.7 | |||
$2.000 | $8.000 | 90.3 | |||
$0.450 | $2.150 | 89.3 | |||
$1.000 | $10.000 | 88.7 | |||
$0.600 | $2.200 | 87.3 | |||
$1.250 | $10.000 | 87.0 | |||
$1.100 | $4.400 | 86.0 | |||
$0.100 | $0.400 | 86.0 | |||
$1.250 | $10.000 | 84.3 | |||
$0.400 | $0.800 | 84.0 | |||
$0.625 | $5.000 | 83.0 | |||
$0.300 | $2.500 | 82.3 | |||
$0.400 | $1.760 | 81.3 | |||
$0.080 | $0.240 | 80.7 | |||
$2.000 | $8.000 | 79.0 | |||
$0.150 | $0.580 | 78.0 | |||
$3.000 | $15.000 | 77.3 | |||
$1.100 | $4.400 | 77.0 | |||
$0.060 | $0.200 | 76.3 | |||
$15.000 | $75.000 | 75.7 | |||
$0.080 | $0.280 | 75.3 | |||
$0.050 | $0.200 | 74.7 | |||
$0.090 | $0.300 | 72.7 | |||
$15.000 | $60.000 | 72.3 | |||
$0.071 | $0.100 | 71.7 | |||
$0.100 | $0.400 | 70.3 | |||
$0.550 | $2.200 | 69.3 | |||
$0.550 | $2.200 | 69.3 | |||
$0.290 | $0.290 | 68.7 | |||
$0.550 | $2.000 | 68.3 | |||
$0.130 | $0.850 | 67.3 | |||
$0.700 | $0.800 | 67.0 | |||
$0.200 | $0.200 | 65.7 | |||
$15.000 | $75.000 | 56.3 | |||
$0.200 | $0.770 | 52.0 | |||
$0.100 | $0.200 | 51.0 | |||
$0.300 | $2.500 | 50.0 | |||
$0.100 | $0.400 | 50.0 | |||
$0.280 | $0.900 | 49.3 | |||
$1.000 | $1.000 | 48.7 | |||
$3.000 | $15.000 | 48.7 | |||
$0.220 | $0.900 | 47.7 | |||
$0.150 | $0.580 | 45.3 | |||
$0.400 | $2.000 | 44.0 | |||
$2.000 | $8.000 | 43.7 | |||
$0.200 | $0.800 | 43.0 | |||
$3.000 | $15.000 | 40.7 | |||
$0.150 | $0.600 | 39.0 | |||
$0.625 | $5.000 | 36.7 | |||
$0.100 | $0.400 | 33.0 | |||
$3.000 | $15.000 | 33.0 | |||
$0.400 | $0.800 | 32.7 | |||
$0.075 | $0.200 | 32.3 | |||
$0.080 | $0.240 | 30.3 | |||
$0.100 | $0.320 | 30.0 | |||
$0.070 | $0.270 | 29.7 | |||
$3.000 | $15.000 | 29.0 | |||
$0.080 | $0.300 | 28.3 | |||
$0.060 | $0.200 | 28.0 | |||
$0.075 | $0.300 | 27.7 | |||
$0.080 | $0.280 | 26.0 | |||
$0.080 | $0.160 | 25.3 | |||
$0.200 | $0.770 | 25.3 | |||
$0.900 | $0.900 | 24.7 | |||
$0.050 | $0.200 | 24.3 | |||
$0.050 | $0.200 | 23.7 | |||
$1.040 | $4.160 | 23.3 | |||
$3.000 | $15.000 | 22.3 | |||
$0.040 | $0.130 | 22.0 | |||
$0.900 | $0.900 | 21.3 | |||
$0.200 | $0.200 | 21.3 | |||
$0.200 | $0.200 | 21.3 | |||
$0.200 | $0.200 | 21.3 | |||
$0.340 | $0.390 | 17.3 | |||
$2.500 | $12.500 | 17.0 | |||
$0.120 | $0.390 | 16.0 | |||
$3.000 | $15.000 | 15.7 | |||
$10.000 | $30.000 | 15.0 | |||
$0.065 | $0.140 | 14.3 | |||
$0.020 | $0.040 | 13.7 | |||
$0.100 | $0.400 | 13.7 | |||
$0.200 | $0.600 | 13.0 | |||
$0.660 | $0.800 | 12.0 | |||
$0.033 | $0.130 | 12.0 | |||
$2.500 | $10.000 | 11.7 | |||
$0.150 | $0.600 | 11.7 | |||
$2.000 | $6.000 | 11.0 | |||
$0.200 | $0.600 | 11.0 | |||
$0.800 | $3.200 | 10.7 | |||
$0.060 | $0.240 | 10.7 | |||
$2.500 | $10.000 | 9.7 | |||
$0.049 | $0.049 | 9.3 | |||
$2.000 | $6.000 | 9.3 | |||
$0.030 | $0.110 | 9.3 | |||
$0.035 | $0.140 | 8.0 | |||
$0.050 | $0.080 | 8.0 | |||
$0.020 | $0.050 | 7.7 | |||
$2.000 | $6.000 | 7.0 | |||
$0.030 | $0.050 | 6.7 | |||
$0.400 | $2.000 | 6.7 | |||
$0.040 | $0.080 | 6.3 | |||
$2.000 | $8.000 | 5.7 | |||
$0.030 | $0.090 | 5.3 | |||
$0.800 | $4.000 | 3.3 | |||
$0.300 | $0.300 | 2.3 | |||
$0.250 | $1.250 | 1.0 | |||
$0.070 | $0.280 | 0.3 | |||
$0.140 | $0.420 | - | |||
$0.500 | $1.500 | - | |||
$1.200 | $1.200 | - | |||
$0.510 | $0.740 | - | |||
$0.030 | $0.040 | - | |||
$0.020 | $0.020 | - |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
Get our weekly newsletter on pricing changes, new releases, and tools.
Deploy OpenClaw in Under 1 Minute— We handle hosting, scaling, and maintenance
About AIME 2024
American Invitational Mathematics Examination 2024 problems testing olympiad-level mathematical reasoning.
This leaderboard shows all models with AIME 2024 benchmark scores, ranked from highest to lowest. Pricing data is included to help you compare performance against cost.
Frequently Asked Questions
Other Benchmark Leaderboards
Built by @aellman
Tools
Directories
Models & Pricing
Endpoints
Rankings
- All Rankings
- All Benchmarks
- Best LLM for Coding
- Best LLM for Math
- Best LLM for Writing
- Best LLM for RAG
- Best Local LLM
- 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.