Text generation and understanding
59
Models
29
Benchmarks
14
Providers
40
Open Weight
58
Deployable Now
39 self-host
59
Structured benchmark-backed rows
0
Signal-backed rows without full normalized tables
0
Benchmark-expected rows still catching up
| # | Model | Economic Footprint | Quality | Params | OSWorld | TAU-Bench | GPQA | GAIA | $/M In | Speed | Open |
|---|---|---|---|---|---|---|---|---|---|---|---|
2 | GPT-5.6 Sol OpenAI Subscription |
| 75.2 |
| 69.6 |
| Undisclosed |
| 62.6 |
| 46.9 |
| 94.6 |
| 77.4 |
$2.00/M Cheapest verified |
| — |
19 | Llama 3.1 8B Instruct Meta Open WeightsStructured | 63.9 | 61.8 | 8B | — | — | 39.5 | 0.7 | Free Cheapest verified | — |
15 | GPT-5.2 Pro OpenAI SubscriptionStructured | 63.8 | 54.8 | Undisclosed | — | 69.8 | 92.4 | 25.2 | $1.25/M Cheapest verified | — |
82 | GPT-4 Turbo OpenAI SubscriptionStructured | 62.8 | 37.7 | Undisclosed | — | — | — | 40.0 | $10.00/M Cheapest verified | — |
5 | GPT-5.4 Pro OpenAI SubscriptionStructured | 62.3 | 43.5 | Undisclosed | 75.0 | 30.7 | 92.8 | 68.1 | $1.25/M Cheapest verified | — |
79 | Llama 3.3 70B Instruct Meta Open WeightsStructured | 61.4 | 60.2 | 70B | — | — | 10.5 | — | $0.1000/M Cheapest verified | — |
89 | Gemma 3 | 60.9 | 63.7 | 4B | — | — | — | — | Free Cheapest verified | — |
106 | Phi 4 Microsoft Open WeightsStructured | 59.7 | 61.4 | 15B | — | — | 57.5 | — | $0.0700/M Cheapest verified | — |
147 | GPT-4.1 OpenAI SubscriptionStructured | 59.1 | 55.0 | Undisclosed | 32.5 | 71.8 | 66.6 | 71.4 | $2.00/M Cheapest verified | — |
100 | Qwen3 235B A22B Qwen Open WeightsStructured | 58.8 | 71.9 | 235B | — | — | — | 44.2 | $0.4550/M Cheapest verified | — |
105 | GPT-5 OpenAI Structured | 57.7 | 39.6 | Undisclosed | 72.0 | — | 94.6 | 0.7 | $1.25/M Cheapest verified | — |
68 | GPT-5.6 Terra OpenAI SubscriptionStructured | 57.3 | 69.5 | Undisclosed | 62.6 | — | 94.6 | 64.1 | $2.00/M Cheapest verified | — |
108 | Mistral Small 3 Mistral AI Open WeightsStructured | 57.2 | 55.4 | 24B | — | — | 46.2 | 20.6 | $0.0500/M Cheapest verified | — |
95 | o3 OpenAI API AccessStructured | 56.1 | 48.0 | Undisclosed | 45.2 | 82.5 | 82.7 | 30.2 | $2.00/M Cheapest verified | — |
107 | Gemma 2 | 54.7 | 51.4 | 27B | — | — | — | — | Free Cheapest verified | — |
113 | Qwen3 235B A22B Thinking 2507 Qwen Open WeightsStructured | 54.0 | 67.2 | 235B | — | — | — | 44.2 | $0.2300/M Cheapest verified | — |
46 | GPT-5.2 OpenAI SubscriptionStructured | 54.0 | 57.7 | Undisclosed | — | 98.7 | 92.4 | 25.2 | $1.25/M Cheapest verified | — |
3 | GPT-5.4 OpenAI SubscriptionStructured | 53.8 | 58.4 | Undisclosed | 75.0 | 98.9 | 92.8 | 68.1 | $1.25/M Cheapest verified | — |
24 | Command A Cohere Open WeightsStructured | 53.6 | 44.0 | Unknown | — | — | 52.7 | — | $2.50/M Cheapest verified | — |
90 | Qwen3.5 397B A17B Qwen Open WeightsStructured | 53.5 | 62.5 | 403B | — | 68.4 | — | 44.2 | $0.5500/M Cheapest verified | — |
91 | Qwen3.8 2.4T A95B Qwen Open WeightsStructured | 53.1 | 59.4 | 2.4T | — | — | 93.5 | 44.2 | $2.00/M Cheapest verified | — |
63 | GPT-5.6 Luna OpenAI SubscriptionStructured | 51.7 | 70.6 | Undisclosed | 62.6 | — | 94.6 | 60.8 | $0.2000/M Cheapest verified | — |
54 | GPT-5.1 OpenAI SubscriptionStructured | 50.4 | 54.9 | Undisclosed | — | 95.6 | 88.1 | 22.9 | $1.25/M Cheapest verified | — |
156 | Llama 3.2 3B Instruct Meta Open WeightsStructured | 49.8 | 47.3 | 3B | — | — | — | — | $0.0500/M Cheapest verified | — |
132 | Qwen2.5-72B Alibaba Open WeightsStructured | 49.5 | 62.9 | 72B | — | — | 20.7 | 4.7 | $0.6000/M Cheapest verified | — |
92 | Qwen3 Coder Next Qwen Open WeightsStructured | 49.3 | 48.9 | 80B | — | — | 73.7 | 44.2 | $0.1200/M Cheapest verified | — |
118 | DeepSeek-R1 DeepSeek Self-HostStructured | 49.2 | 76.7 | 671B | — | — | 71.5 | 13.0 | $0.2800/M Cheapest verified | — |
259 | Llama 3 70B Instruct Meta Open WeightsStructured | 49.1 | 58.0 | 70B | — | — | 39.5 | 14.0 | $0.5100/M Cheapest verified | — |
121 | DeepSeek-V3 DeepSeek Open WeightsStructured | 49.0 | 70.2 | 685B | — | — | 59.1 | 13.0 | $0.2800/M Cheapest verified | 145 tok/s |
119 | Llama 4 Maverick Meta Open WeightsStructured | 47.7 | 70.0 | 400B | 15.3 | 45.7 | 67.1 | — | Free Cheapest verified | 88 tok/s |
266 | Nemotron 70B NVIDIA Open WeightsStructured | 47.7 | 64.9 | 70B | — | — | — | — | Free Cheapest verified | — |
85 | Grok 4.3 xAI SubscriptionStructured | 46.9 | 61.6 | 3.0T | — | 18.0 | 87.7 | — | $1.25/M Cheapest verified | — |
22 | DeepSeek V3.1 Terminus DeepSeek Open WeightsStructured | 45.7 | 46.7 | 671B | — | — | — | 13.0 | $0.2700/M Cheapest verified | — |
102 | Kimi K2 Moonshot AI SubscriptionStructured | 45.4 | 49.3 | 1.0T | — | — | 76.6 | — | $0.5700/M Cheapest verified | — |
115 | Qwen3 Next 80B A3B Thinking Qwen Open WeightsStructured | 45.3 | 48.0 | 81B | — | — | — | 44.2 | $0.1500/M Cheapest verified | — |
223 | grok-4 xAI SubscriptionStructured | 45.0 | 64.8 | 3.0T | — | 18.0 | 87.7 | — | $3.00/M Cheapest verified | — |
256 | Grok-2 xAI SubscriptionStructured | 45.0 | 41.3 | Undisclosed | — | — | — | — | $2.00/M Cheapest verified | — |
10 | GPT-5.6 Sol Pro OpenAI SubscriptionStructured | 44.9 | 41.8 | Undisclosed | 62.6 | — | 94.6 | — | $4.00/M Cheapest verified | — |
122 | Qwen3-235B Alibaba Open WeightsStructured | 44.8 | 72.2 | 235B | 14.7 | 48.1 | — | 44.2 | $0.8000/M Cheapest verified | 72 tok/s |
301 | QwQ 32B Qwen Open WeightsStructured | 44.7 | 68.9 | 33B | — | — | 59.3 | 40.6 | $0.1500/M Cheapest verified | — |
97 | Qwen3.7 Max Qwen Open WeightsStructured | 43.0 | 41.2 | Unknown | — | — | 92.3 | 44.2 | $1.48/M Cheapest verified | — |
11 | GPT-5.6 Terra Pro OpenAI SubscriptionStructured | 42.1 | 41.8 | Undisclosed | 62.6 | — | 94.6 | — | $2.00/M Cheapest verified | — |
47 | Qwen3 Max Thinking Qwen Open WeightsStructured | 41.3 | 25.4 | Unknown | — | — | 86.1 | 44.2 | $0.7800/M Cheapest verified | — |
263 | DeepSeek-R1-Distill-Qwen-1.5B DeepSeek Open WeightsStructured | 39.0 | 52.0 | 2B | — | — | — | 13.0 | Free Free | — |
249 | DeepSeek-R1-0528-Qwen3-8B DeepSeek Open WeightsStructured | 38.7 | 55.2 | 8B | — | 63.9 | 81.0 | 13.0 | Free Free | — |
299 | DeepSeek-R1-Distill-Qwen-7B DeepSeek Open WeightsStructured | 38.4 | 50.3 | 8B | — | — | — | 3.7 | Free Free | — |
302 | DeepSeek-R1-Distill-Llama-8B DeepSeek Open WeightsStructured | 38.2 | 50.7 | 8B | — | — | — | 13.0 | Free Free | — |
4 | GPT-5.6 Luna Pro OpenAI SubscriptionStructured | 37.1 | 41.8 | Undisclosed | 62.6 | — | 94.6 | — | $0.2000/M Cheapest verified | — |
248 | deepseek-v3.1 DeepSeek Open WeightsStructured | 36.7 | 71.6 | 671B | — | — | — | 13.0 | $0.2800/M Cheapest verified | — |
412 | DeepSeek-R1-Zero DeepSeek Open WeightsStructured | 36.7 | 49.0 | 671B | — | — | — | 13.0 | Free Free | — |
241 | DeepSeek-V3.2 DeepSeek Open WeightsStructured | 36.2 | 68.2 | Unknown | 18.9 | — | — | 13.0 | $0.2800/M Cheapest verified | — |
279 | qwen3-235b-a22b-instruct-2507 Qwen Open WeightsStructured | 35.4 | 73.9 | 235B | — | — | — | 44.2 | Free Free | — |
382 | MiniMax-M2.5 MiniMax Open WeightsStructured | 33.0 | 57.6 | 229B | — | — | 84.8 | — | $0.3000/M Cheapest verified | — |
127 | DeepSeek V3.2 Speciale DeepSeek Open WeightsStructured | 32.9 | 50.2 | Unknown | — | — | 87.1 | 13.0 | $0.2800/M Cheapest verified | — |
225 | DeepSeek-V4-Pro DeepSeek Ready to UseStructured | 32.7 | 64.8 | 1.6T | — | — | 90.1 | 13.0 | Free Free | — |
934 | Qwen3-0.6B Qwen Open WeightsStructured | 32.2 | 44.4 | 752M | — | — | — | 44.2 | Free Free | — |
317 | MiniMax-M2 MiniMax Open WeightsStructured | 32.1 | 54.3 | 229B | — | — | 77.7 | — | Free Free | — |
255 | GLM-5.2 Z.ai Open WeightsStructured | 28.8 | 60.3 | 753B | — | 37.1 | 91.2 | 22.9 | Free Free | — |
361 | GLM-4.5-Air Z.ai Open WeightsStructured | 28.5 | 54.0 | 110B | — | — | 73.3 | — | Free Free | — |