LLM Models
21 models
Data: OpenRouter and official sources · refreshed daily · as of 9/15/2026
| # | Model ↕ | Provider ↕ | Score ↕? | Context ↕? | Speed ↕? | MMLU ↕? | GPQA ↕? | HumanEval ↕? | SWE-B ↕? | Input $/1M ↕? | Output $/1M ↕? | ⭐ Top ↓? | OSS ↕? | Released ↕? |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | Meta | - | 1M | - | - | - | - | - | $0.100 | $0.200 | - | - | Aug 2026 | |
2 | Meta | - | 131K | - | - | - | - | - | $0.175 | $0.750 | - | - | Aug 2026 | |
3 | Meta | - | 1M | - | - | - | - | - | $1.25 | $4.25 | - | - | Aug 2026 | |
4 | Meta | - | 1M | - | - | - | - | - | $1.25 | $4.25 | - | - | Jul 2026 | |
5 | Meta | - | 164K | - | - | - | - | - | $0.180 | $0.180 | - | - | Apr 2025 | |
6 | Meta | - | 10M | - | - | - | - | - | $0.100 | $0.300 | - | - | Apr 2025 | |
7 | Meta | - | 1M | - | - | - | - | - | $0.188 | $0.652 | - | - | Apr 2025 | |
8 | Meta | - | 131K | - | - | - | - | - | $0.484 | $0.030 | - | - | Feb 2025 | |
9 | Meta | - | 131K | - | - | - | - | - | $0.100 | $0.320 | - | ✓ OSS | Dec 2024 | |
10 | Meta | - | 131K | - | - | - | - | - | $0.345 | $0.345 | - | - | Sep 2024 | |
11 | Meta | - | 131K | - | - | - | - | - | $0.050 | $0.330 | - | ✓ OSS | Sep 2024 | |
12 | Meta | - | 131K | - | - | - | - | - | $0.027 | $0.201 | - | ✓ OSS | Sep 2024 | |
13 | Meta | - | 131K | - | - | - | - | - | $0.400 | $0.400 | - | ✓ OSS | Jul 2024 | |
14 | Meta | - | 131K | - | - | - | - | - | $0.050 | $0.080 | - | ✓ OSS | Jul 2024 | |
15 | Meta | - | 8K | - | - | - | - | - | $0.140 | $0.140 | - | ✓ OSS | Apr 2024 | |
16 | Meta | - | 8K | - | - | - | - | - | $0.510 | $0.740 | - | - | Apr 2024 | |
17 | Meta | 64 | 128K | 60 | 88.6 | 50.7 | 89.0 | 34.1 | - | - | - | ✓ OSS | - | |
18 | Meta | 56 | 128K | 150 | 83.6 | 46.7 | 80.5 | 21.8 | - | - | - | ✓ OSS | - | |
19 | Meta | 37 | 128K | 500 | 63.4 | 24.7 | 58.3 | 9.5 | - | - | - | ✓ OSS | - | |
20 | Meta | - | 1M | - | - | - | - | - | $0.100 | $0.200 | - | - | - | |
21 | Meta | - | 1M | - | - | - | - | - | $1.25 | $4.25 | - | - | - |
Score = MMLU×20% + GPQA×30% + HumanEval×25% + SWE-Bench×25%⭐ Top - average TECHAGENT user ratingtok/s - output tokens/sec via API
Don't see a model you know? Sign in to suggest it.