298 models in catalog
AI models
Every model we track — frontier flagships, open-weights specialists, narrow benchmarks-only releases. Filter by lab, country, access, modality, or release window. Sorted by newest by default; head to the leaderboard for the ranked view.
Leaderboard →Labs →Benchmarks →
Updated May 29, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Spotted an error?
| Rank | Model | Math idx ↓ | MATH-500 | FrontierMath | HMMT 2025 | GSM8K | MGSM | AIME 2024 | AIME 2025 | MATH | Released | Country | Type | Access | Params | Cutoff | Context | Speed | Latency | In $/M | Out $/M |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| #126 | 54.5 | 88.3 | — | — | — | — | — | 20.7 | — | 2025 | — | llm | — | — | — | — | — | — | $0.10 | $0.30 | |
| #127 | 54.3 | 92.5 | — | 35 | — | — | 49.6 | 40.2 | — | 2025 | — | multimodal | API only | — | 2024 | 1M | 150 | 5.00 | $0.40 | $1.60 | |
| #128 | 54.1 | 88.9 | — | — | — | 92.3 | — | 19.3 | 61.2 | 2025 | — | multimodal | Open weights | 400B total / 17B active (MoE) | 2024 | 1M | 639 | 0.20 | $0.15 | $0.60 | |
| #129 | 53.7 | 91.3 | — | 28.9 | — | — | 48.1 | 46.4 | 87 | 2025 | — | multimodal | API only | — | 2024 | 1M | 100 | 10.00 | $2.00 | $8.00 | |
| #130 | 52.3 | — | — | — | — | — | — | 52.3 | — | 2025 | — | llm | — | — | — | — | — | — | $0.00 | $0.00 | |
| #131 | 52.3 | — | — | — | — | — | — | 52.3 | — | 2025 | — | llm | — | — | — | — | 103 | 1.04 | $0.30 | $1.00 | |
| #132 | 51.8 | 90.2 | — | — | — | — | 39.2 | 26 | — | 2024 | — | llm | Open weights | 671B total / 37B active (MoE) | 2024 | 131K | 100 | 0.50 | $0.23 | $0.91 | |
| #133 | 51.8 | 85.3 | — | — | — | — | — | 18.3 | — | 2025 | — | llm | — | — | — | — | — | — | $0.10 | $0.30 | |
| #134 |  Amazon | 50.6 | 83.9 | — | — | — | — | — | 17.3 | — | 2025 | — | llm | — | — | — | — | 40 | 1.31 | $2.50 | $12.50 |
| #135 | 50.3 | — | — | — | — | — | — | 50.3 | — | 2025 | — | llm | — | — | — | — | — | — | $0.00 | $0.00 | |
| #136 | 49.9 | — | — | 33.5 | — | — | 66.3 | 49.8 | — | 2025 | — | llm | Open weights | 671B (37B active) | 2025 | 164K | — | — | $0.21 | $0.79 | |
| #137 | 49.9 | 85.8 | — | — | 95.8 | — | — | 14 | 83.1 | 2024 | — | llm | Open weights | — | 2024 | 131K | 100 | 0.37 | $0.36 | $0.40 | |
| #138 | 49.9 | 49.9 | — | — | — | — | — | — | — | 2024 | — | llm | Open weights | — | 2023 | 8K | 81 | 0.51 | $0.04 | $0.04 | |
| #139 | 49.5 | 81 | — | — | — | 80.6 | — | 18 | 80.4 | 2025 | — | llm | Open weights | — | 2024 | 16K | 33 | 0.20 | $0.07 | $0.14 | |
| #140 | InclusionAI | 49.3 | — | — | — | — | — | — | 49.3 | — | 2025 | — | llm | — | — | — | — | — | — | $0.00 | $0.00 |
| #141 | 49.2 | 84.4 | — | — | — | 90.6 | — | 14 | 50.3 | 2025 | — | multimodal | Open weights | 109B total / 17B active (MoE) | 2024 | 10M | 776 | 0.31 | $0.08 | $0.30 | |
| #142 | 48.9 | 68.4 | — | — | — | — | — | 29.3 | — | 2025 | — | llm | — | — | — | — | 190 | 0.42 | $0.10 | $0.30 | |
| #143 | 48.3 | 48.3 | — | — | — | — | — | — | — | 2024 | — | llm | Open weights | — | 2023 | 8K | 45 | 0.70 | $0.51 | $0.74 | |
| #144 | 47.5 | 81.9 | — | — | — | — | — | 13 | — | 2025 | — | llm | Open weights | — | 2024 | 256K | 203 | 0.17 | $2.50 | $10.00 | |
| #145 | 46.5 | 75 | — | — | — | — | — | 18 | — | 2025 | — | llm | — | — | — | — | 225 | 0.95 | $0.10 | $1.30 | |
| #146 | 46.1 | 84.8 | — | — | — | — | 29.4 | 24 | — | 2025 | — | multimodal | API only | — | 2024 | 1M | 200 | 2.00 | $0.10 | $0.40 | |
| #147 | 45.7 | 77.1 | — | — | — | — | — | 14.3 | — | 2025 | — | llm | — | — | — | — | 56 | 0.55 | $0.00 | $0.00 | |
| #148 | 44.7 | 76.6 | — | — | — | — | — | 12.7 | — | 2025 | — | llm | — | — | — | — | — | — | $0.00 | $0.10 | |
| #149 | 43.8 | 73.6 | — | — | 93 | — | — | 14 | — | 2024 | — | llm | Open weights | 123B | — | 128K | 42 | 0.40 | $2.00 | $6.00 | |
| #150 | 43.3 | — | — | — | — | — | — | 43.3 | — | 2025 | — | llm | — | — | — | — | — | — | $0.00 | $0.00 |
Ranked on Math. Cell colors show relative standing within each column (red → yellow → green). Scores are curated approximations — see each model for sources.