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 | General idx ↓ | Multi-IF | LiveBench | Arena Hard | Humanity’s Last Exam | IFEval | SimpleQA | MMLU-Pro | MMLU | Released | Country | Type | Access | Params | Cutoff | Context | Speed | Latency | In $/M | Out $/M |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| #76 | 80.5 | — | — | — | 9.8 | — | — | 80.5 | — | 2025 | — | llm | — | — | — | — | 151 | 1.18 | $0.30 | $1.90 | |
| #77 | 80.5 | — | — | — | 4.8 | — | — | 80.5 | 85.5 | 2025 | — | multimodal | Open weights | 400B total / 17B active (MoE) | 2024 | 1M | 639 | 0.20 | $0.15 | $0.60 | |
| #78 | 80.5 | — | — | — | 7 | — | — | 80.5 | — | 2025 | — | llm | — | — | — | — | — | — | $0.00 | $0.00 | |
| #79 | 80.5 | — | — | — | 4 | 92.1 | — | 68.9 | 86 | 2024 | — | llm | Open weights | — | 2023 | 131K | 2220 | 0.50 | $0.10 | $0.32 | |
| #80 | 80.3 | — | 77.1 | 95.6 | 11.7 | — | — | 68.2 | 87.8 | 2025 | — | llm | Open weights | — | 2025 | 131K | 68 | 0.78 | $0.46 | $1.82 | |
| #81 | 80 | — | — | — | 9.7 | — | — | 80 | — | 2025 | — | llm | API only | — | 2025 | 200K | 100 | 0.30 | $1.00 | $5.00 | |
| #82 | 80 | — | — | — | 5.1 | — | — | 80 | — | 2025 | — | multimodal | API only | — | 2024 | 128K | 100 | 0.70 | $3.00 | $15.00 | |
| #83 | 79.9 | — | — | — | 8.9 | — | — | 79.9 | — | 2025 | — | multimodal | Open weights | — | — | 131K | 44 | 1.31 | $0.30 | $0.90 | |
| #84 | 79.6 | 70.8 | — | — | 5.4 | 87.4 | — | 80.6 | 90.2 | 2025 | — | multimodal | API only | — | 2024 | 1M | 100 | 10.00 | $2.00 | $8.00 | |
| #85 | Motif Technologies | 79.6 | — | — | — | 8.2 | — | — | 79.6 | — | 2025 | — | llm | — | — | — | — | — | — | $0.00 | $0.00 |
| #86 | 79.5 | — | — | — | 6.1 | — | — | 79.5 | — | 2025 | — | llm | Open weights | 70600000000 | — | 128K | 37 | 0.65 | $0.10 | $0.40 | |
| #87 | 79.4 | — | — | — | 10.2 | — | — | 79.4 | — | 2025 | — | llm | — | — | — | — | 148 | 0.30 | $0.10 | $0.20 | |
| #88 | 79.3 | — | — | — | 7.5 | — | — | 79.3 | — | 2025 | — | llm | — | — | — | — | — | — | $0.00 | $0.00 | |
| #89 | InclusionAI | 79.3 | — | — | — | 8.9 | — | — | 79.3 | — | 2025 | — | llm | — | — | — | — | — | — | $0.10 | $0.60 |
| #90 | 79.2 | — | — | — | 7.3 | — | — | 79.2 | — | 2025 | — | llm | — | — | — | — | 102 | 1.05 | $0.30 | $1.00 | |
| #91 | 79.1 | — | — | — | 6.3 | — | — | 79.1 | — | 2025 | — | multimodal | Open weights | — | — | 262K | 76 | 1.16 | $0.10 | $0.42 | |
| #92 | ServiceNow | 79 | — | — | — | 9.8 | — | — | 79 | — | 2025 | — | llm | — | — | — | — | — | — | $0.00 | $0.00 |
| #93 | 78.8 | — | — | — | 4.4 | — | — | 78.8 | — | 2025 | — | llm | — | — | — | — | 69 | 1.68 | $0.30 | $1.80 | |
| #94 | 78.8 | 72.2 | 74.3 | 91 | 6.6 | — | — | 77.7 | — | 2025 | — | llm | Open weights | — | 2025 | 131K | 122 | 0.66 | $0.09 | $0.45 | |
| #95 | 78.8 | — | — | — | 5.9 | — | — | 78.8 | — | 2025 | — | multimodal | Open weights | — | 2024 | 66K | 85 | 0.70 | $0.60 | $1.80 | |
| #96 | MBZUAI Institute of Foundation Models | 78.6 | — | — | — | 9.8 | — | — | 78.6 | — | 2025 | — | llm | — | — | — | — | — | — | $0.00 | $0.00 |
| #97 | Naver | 78.5 | — | — | — | 5.5 | — | — | 78.5 | — | 2025 | — | llm | — | — | — | — | — | — | $0.00 | $0.00 |
| #98 | 78 | — | — | — | 8.7 | — | — | 78 | — | 2025 | — | llm | API only | — | 2024 | 400K | 500 | 0.30 | $0.05 | $0.40 | |
| #99 | 77.8 | — | 73.1 | — | 8.2 | 83.9 | — | 76.4 | — | 2025 | — | llm | Open weights | 32500000000 | 2024 | — | 31 | 0.45 | $0.70 | $1.00 | |
| #100 | InclusionAI | 77.7 | — | — | — | 6.3 | — | — | 77.7 | — | 2025 | — | llm | — | — | — | — | 91 | 1.61 | $0.10 | $0.60 |
Ranked on General. Cell colors show relative standing within each column (red → yellow → green). Scores are curated approximations — see each model for sources.