Get real-time LLM pricing in Claude Code and Cursor. Try Price Per Token MCP
AIME 2025 Leaderboard
American Invitational Mathematics Examination 2025 problems testing olympiad-level mathematical reasoning.
Data from Artificial Analysis
As of March 15, 2026, the top-scoring model on AIME 2025 is GPT-5.2 Pro at 99.0%, followed by GPT-5 Codex at 98.7% and Gemini 3 Flash Preview at 97.0%. 173 models have been evaluated on this benchmark.
Last updated: March 15, 2026
Models
173
Best Score
99.0
Average
51.8
Std Dev
30.7
Categories
Mathematical Problem Solving
SourceArtificial Analysis
Provider | Model | Input $/M | Output $/M | AIME 2025 | Actions |
|---|---|---|---|---|---|
$10.500 | $84.000 | 99.0 | |||
$1.250 | $10.000 | 98.7 | |||
$0.500 | $3.000 | 97.0 | |||
$0.400 | $1.200 | 96.7 | |||
$0.090 | $0.290 | 96.3 | |||
$1.250 | $10.000 | 95.7 | |||
$2.000 | $12.000 | 95.7 | |||
$0.380 | $1.750 | 95.0 | |||
$0.550 | $2.200 | 94.7 | |||
$0.207 | $0.828 | 94.7 | |||
$1.250 | $10.000 | 94.3 | |||
$1.250 | $10.000 | 94.0 | |||
$0.039 | $0.100 | 93.4 | |||
$3.000 | $15.000 | 92.7 | |||
$0.260 | $0.380 | 92.0 | |||
$1.250 | $10.000 | 91.7 | |||
$0.250 | $2.000 | 91.7 | |||
$5.000 | $25.000 | 91.3 | |||
$0.110 | $0.600 | 91.0 | |||
$0.050 | $0.200 | 91.0 | |||
$1.100 | $4.400 | 90.7 | |||
$0.250 | $2.000 | 90.7 | |||
$0.150 | $0.750 | 89.7 | |||
$0.200 | $0.500 | 89.7 | |||
$0.210 | $0.790 | 89.7 | |||
$0.030 | $0.100 | 89.3 | |||
$0.200 | $0.500 | 89.3 | |||
$2.000 | $8.000 | 88.3 | |||
$3.000 | $15.000 | 88.0 | |||
$0.200 | $1.100 | 88.0 | |||
$1.000 | $10.000 | 87.7 | |||
$0.270 | $0.410 | 87.7 | |||
$0.390 | $1.740 | 86.0 | |||
$0.300 | $0.900 | 85.3 | |||
$0.250 | $0.500 | 84.7 | |||
$0.050 | $0.400 | 83.7 | |||
$1.000 | $5.000 | 83.7 | |||
$1.250 | $10.000 | 83.0 | |||
$0.200 | $0.200 | 82.7 | |||
$0.270 | $0.950 | 82.7 | |||
$0.780 | $3.900 | 82.3 | |||
$0.400 | $0.800 | 82.0 | |||
$0.130 | $0.850 | 80.7 | |||
$1.200 | $6.000 | 80.7 | |||
$15.000 | $75.000 | 80.3 | |||
$0.050 | $0.400 | 78.3 | |||
$0.255 | $1.000 | 78.3 | |||
$0.150 | $0.500 | 77.3 | |||
$0.100 | $0.400 | 76.7 | |||
$0.450 | $2.150 | 76.0 | |||
$1.200 | $6.000 | 75.0 | |||
$0.200 | $0.200 | 75.0 | |||
$3.000 | $15.000 | 74.3 | |||
$0.600 | $2.200 | 73.7 | |||
$0.150 | $0.500 | 73.7 | |||
$15.000 | $75.000 | 73.3 | |||
$0.300 | $2.500 | 73.3 | |||
$0.080 | $0.240 | 73.0 | |||
$0.600 | $1.800 | 73.0 | |||
$0.080 | $0.280 | 72.3 | |||
$0.130 | $0.520 | 72.3 | |||
$0.071 | $0.100 | 71.7 | |||
$0.200 | $0.880 | 70.7 | |||
$0.120 | $0.200 | 70.7 | |||
$1.000 | $3.000 | 69.7 | |||
$0.040 | $0.160 | 69.7 | |||
$0.130 | $0.400 | 68.7 | |||
$0.100 | $0.400 | 68.7 | |||
$0.104 | $0.416 | 68.3 | |||
$0.550 | $2.190 | 68.0 | |||
$0.090 | $0.290 | 67.7 | |||
$0.039 | $0.100 | 66.7 | |||
$0.090 | $0.300 | 66.3 | |||
$0.090 | $0.780 | 66.3 | |||
$0.290 | $0.290 | 63.0 | |||
$5.000 | $25.000 | 62.7 | |||
$0.040 | $0.160 | 62.3 | |||
$0.300 | $2.500 | 60.3 | |||
$0.260 | $0.380 | 59.0 | |||
$0.060 | $0.200 | 58.0 | |||
$3.000 | $15.000 | 58.0 | |||
$0.270 | $0.410 | 57.7 | |||
$0.400 | $2.000 | 57.3 | |||
$0.550 | $2.200 | 57.0 | |||
$3.000 | $15.000 | 56.3 | |||
$0.060 | $0.200 | 55.7 | |||
$0.500 | $3.000 | 55.7 | |||
$0.700 | $0.800 | 53.7 | |||
$0.210 | $0.790 | 53.7 | |||
$0.100 | $0.400 | 53.3 | |||
$0.200 | $0.200 | 52.3 | |||
$0.875 | $7.000 | 51.0 | |||
$0.150 | $0.750 | 49.7 | |||
$0.380 | $1.750 | 48.0 | |||
$0.100 | $0.400 | 46.7 | |||
$0.400 | $1.600 | 46.3 | |||
$0.390 | $1.740 | 44.3 | |||
$0.200 | $1.500 | 43.3 | |||
$0.280 | $0.900 | 41.3 | |||
$0.200 | $0.500 | 41.3 | |||
$0.100 | $0.200 | 41.3 | |||
$0.200 | $0.770 | 41.0 | |||
$0.220 | $0.900 | 39.3 | |||
$1.000 | $5.000 | 39.0 | |||
$0.400 | $2.000 | 38.3 | |||
$3.000 | $15.000 | 38.0 | |||
$1.250 | $10.000 | 38.0 | |||
$3.000 | $15.000 | 37.0 | |||
$0.400 | $0.900 | 36.7 | |||
$15.000 | $75.000 | 36.3 | |||
$0.100 | $0.400 | 35.3 | |||
$2.000 | $8.000 | 34.7 | |||
$0.200 | $0.500 | 34.3 | |||
$0.300 | $2.500 | 33.7 | |||
$1.250 | $10.000 | 31.7 | |||
$0.150 | $0.150 | 31.7 | |||
$0.400 | $2.000 | 30.3 | |||
$0.200 | $0.200 | 30.0 | |||
$0.070 | $0.280 | 29.3 | |||
$0.150 | $0.400 | 29.0 | |||
$0.070 | $0.270 | 29.0 | |||
$0.050 | $0.400 | 27.3 | |||
$0.080 | $0.200 | 27.3 | |||
$0.060 | $0.180 | 27.0 | |||
$0.200 | $0.200 | 26.7 | |||
$0.300 | $0.900 | 26.3 | |||
$0.200 | $0.770 | 26.0 | |||
$0.010 | $0.020 | 25.3 | |||
$0.050 | $0.200 | 24.3 | |||
$0.100 | $0.400 | 24.0 | |||
$0.400 | $0.800 | 23.7 | |||
$0.200 | $0.200 | 22.3 | |||
$0.100 | $0.400 | 21.7 | |||
$0.080 | $0.280 | 21.7 | |||
$3.000 | $15.000 | 21.0 | |||
$0.030 | $0.110 | 20.7 | |||
$0.080 | $0.240 | 19.7 | |||
$0.150 | $0.600 | 19.3 | |||
$0.050 | $0.200 | 19.0 | |||
$0.040 | $0.130 | 18.3 | |||
$0.060 | $0.140 | 18.0 | |||
$2.500 | $12.500 | 17.3 | |||
$0.600 | $1.800 | 15.3 | |||
$1.000 | $3.000 | 15.3 | |||
$0.150 | $0.600 | 14.7 | |||
$0.020 | $0.040 | 14.3 | |||
$0.120 | $0.390 | 14.0 | |||
$2.000 | $6.000 | 14.0 | |||
$0.080 | $0.300 | 14.0 | |||
$0.400 | $1.760 | 13.7 | |||
$0.050 | $0.200 | 13.3 | |||
$2.500 | $10.000 | 13.0 | |||
$0.040 | $0.080 | 12.7 | |||
$0.130 | $0.400 | 11.3 | |||
$0.900 | $0.900 | 11.0 | |||
$0.100 | $0.400 | 8.0 | |||
$0.100 | $0.320 | 7.7 | |||
$0.800 | $3.200 | 7.0 | |||
$0.060 | $0.240 | 7.0 | |||
$0.035 | $0.140 | 6.0 | |||
$0.400 | $2.000 | 4.7 | |||
$0.020 | $0.050 | 4.3 | |||
$0.050 | $0.080 | 4.3 | |||
$0.340 | $0.390 | 4.0 | |||
$0.100 | $0.300 | 3.7 | |||
$0.030 | $0.050 | 3.3 | |||
$0.050 | $0.200 | 3.3 | |||
$0.900 | $0.900 | 3.0 | |||
$2.000 | $6.000 | 2.3 | |||
$2.000 | $8.000 | 2.3 | |||
$0.049 | $0.049 | 1.7 | |||
$0.020 | $0.020 | - | |||
$2.000 | $6.000 | - |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
108 out of our 483 tracked models have had a price change in March.
Get our weekly newsletter on pricing changes, new releases, and tools.
About AIME 2025
American Invitational Mathematics Examination 2025 problems testing olympiad-level mathematical reasoning.
This leaderboard shows all models with AIME 2025 benchmark scores, ranked from highest to lowest. Pricing data is included to help you compare performance against cost.
Frequently Asked Questions
Other Benchmark Leaderboards
GPQA
Reasoning and Logic
Humanity's Last Exam
Reasoning and Logic
SciCode
Computer Science and Programming
IFBench
Instruction Following
LCR
Reasoning and Logic
Tau2
Multi-turn
TerminalBench
Multi-turn
MMLU-Pro
General Knowledge
LiveCodeBench
Computer Science and Programming
AGIEval English
Reasoning and Logic
MATH-500
Mathematical Problem Solving
AIME 2024
Mathematical Problem Solving
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 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.